Streaming video understanding requires multimodal large language models (MLLMs) to process continuous visual inputs and respond to user queries under strict causality and bounded memory. Existing approaches typically compress historical observations into an external memory bank and retrieve query-relevant evidence as additional visual context. Though effective, this store-and-retrieve paradigm keeps historical evidence as external visual context, preventing it from being internalized into a compact, evolving latent memory that can continuously guide streaming reasoning. To bridge this gap, we introduce LatentStream, a progressive latent working memory framework that shifts streaming memory from store-and-retrieve to retrieve-and-internalize. Specifically, LatentStream comprises three coordinated components. First, Query-agnostic Hierarchical Streaming Memory organizes visual history into short-, mid-, and long-term levels under a fixed memory budget through Jenks-guided adaptive consolidation. Once a query arrives, Hierarchical Latent Memory Evolution equips groups of latent memory tokens with progressively expanding memory receptive fields, enabling them to iteratively retrieve historical evidence from their corresponding scopes and internalize it into a compact, fixed-length latent memory. Finally, Progressive Confidence-guided Latent Memory Optimization constructs a hierarchical progression reward from group-wise predictive entropy and jointly refines the latent memory tokens and retrieved evidence, encouraging increasingly confident streaming reasoning. Extensive experiments demonstrate that LatentStream achieves new state-of-the-art results on existing online and offline video benchmarks.
Junqing Du, Fernando Ropero, Erkin Turkoz +2cs.CV cs.AI cs.RO
3D spatial reasoning underpins understanding and acting in the physical world, yet it remains unreliable in current multimodal large language models (MLLMs). These models falter at precise geometric measurement, at transforming between egocentric and allocentric viewpoints, and at grounding fine-grained appearance. The most common remedies fine-tune the model on large-scale curated spatial-reasoning datasets or attach dedicated encoders for 3D geometry, which typically couples the solution to costly supervision and a specific backbone. We instead introduce GraFT, a training-free framework that supplies the missing 3D structure through a compact, easily maintained 3D scene graph (3DSG). From this 3DSG, GraFT provides three spatial reasoning capabilities: (1) deterministic geometry through symbolic tools, (2) allocentric layout through a bird's-eye-view (BEV) rendering, and (3) visual-attribute grounding through task-relevant egocentric frames. On ScanQA, GraFT improves every metric over the same-backbone baseline, raising CIDEr by 27%. On VSI-Bench, GraFT improves frozen MLLMs by up to 65%, surpassing every proprietary and general-purpose open-source baseline, and several prominent fine-tuned spatial models.
Multimodal large language models have achieved remarkable progress in front-end web development, generating interactive webpages from multimodal references such as screenshots and interaction videos. However, existing work largely emphasizes visual metrics such as aesthetics and layout similarity, while overlooking the more critical validation of interactive functionality. We present RILA, an execution-driven agent that puts browser rendering in the loop, iteratively editing generated code from runtime interaction feedback. RILA introduces an Action Interaction Verification (AIV) module that replays the reference interaction trajectory on the generated webpage to collect grounded execution-aware observations, and an Execution-aware Rendering Score (ERS) that jointly measures interaction correctness and visual fidelity to guide iterative optimization. We further build an execution-verified data synthesis pipeline that produces diverse, high-quality training data, offering gains complementary to inference-time optimization. On IWR-Bench, RILA consistently improves both interaction and visual fidelity across foundation models. Notably, with our training pipeline, RILA lifts the compact Qwen3.5-9B backbone from 40.40% to 57.52%, surpassing far larger one-shot generators, including the 1T-parameter Kimi-K2.6 (55.61%) and the proprietary GPT-5.5 (55.74%).
Visual token pruning reduces the inference overhead of multimodal large language models (MLLMs) by retaining only a subset of visual tokens. Existing methods usually select tokens based on importance or redundancy. However, we observe that these criteria produce stable spatial biases across inputs and do not always outperform simple Uniform Grid sampling, highlighting the value of broad spatial coverage. Motivated by this, we propose S$^2$Prune, a training-free pruning method that preserves spatial coverage while adapting token density to local image structure. We first divide the image into regions and assign at least one token to each region to preserve coverage. The remaining token budget is then distributed according to Laplacian variation, giving more tokens to regions with richer structure. We then use Early Representation Change (ERC), computed from the first decoder block, to select representative tokens within each region. We evaluate S$^2$Prune across diverse settings and two MLLM architectures. On Qwen2.5-VL-7B-Instruct, it achieves the highest average accuracy among the evaluated training-free pruning methods. With only 32 of the original 576 visual tokens, it still retains 79.3% of the full-model performance. Code is available at https://github.com/yuanyuanjia71-spec/S2Prune.
Despite their strong multimodal understanding ability, multimodal large language models (MLLMs) incur substantial computational overhead when processing long visual token sequences. To reduce inference costs, recent studies have explored visual token pruning through vision-centric or text-guided strategies. However, these methods often overlook high-norm outlier tokens, i.e., tokens with abnormally large feature norms, leading to suboptimal pruning decisions. In this work, we show that such high-norm outlier tokens are highly redundant in both feature and spatial dimensions, yet are often mistakenly preserved as informative cues by existing methods. Motivated by this observation, we propose SinkPruner, a training-free visual token pruning framework for efficient MLLM inference. SinkPruner follows a coarse-to-fine design with two key modules: a visual sanitizer that filters high-norm redundancies and alleviates attention sink and attention dispersion, and a text-guided pruner that further retains tokens semantically aligned with the text query. Extensive experiments on twelve image-language and four video-language benchmarks demonstrate the effectiveness, efficiency, and generalizability of our framework. Notably, SinkPruner preserves 96.5% (91.8%) of the original performance of LLaVA-1.5 (Qwen2.5-VL) under an 89% token reduction. Experiments further indicate that our visual sanitizer exhibits promising transferability in enhancing the performance of existing pruning methods. Our code is available at https://github.com/LaVi-Lab/SinkPruner.
Existing research on object hallucination in multimodal large language models (MLLMs) predominantly attributes the problem to language priors such as over-reliance on textual co-occurrence statistics. We challenge this view by presenting quantitative evidence for a complementary, under-explored cause: visual-origin hallucination, where hallucinations arise from incorrect visual feature extraction and misalignment between image and text embeddings. Through cosine similarity analysis and Smooth Grad-CAM entropy measurements, we show that hallucinated samples exhibit systematically lower image-text similarity (average 0.158 vs. -0.122) and inverted attention patterns, where attention is dispersed when the target object is present but wrongly concentrated when it is absent. Guided by this diagnosis, we propose Adversarial Contrastive Fine-Tuning (ACFT). ACFT uses an Adversarial Hallucination Attribute Flipping (AHAF) procedure, involving minimal, targeted adversarial perturbations that flip an image's hallucination attribute, to construct perfectly aligned positive-negative pairs, which are then used for contrastive fine-tuning. AHAF simultaneously serves as a diagnostic probe, revealing that MLLM visual representations lie dangerously close to hallucination decision boundaries. Requiring only 0.9% of the COCO dataset and adding zero inference overhead, ACFT achieves state-of-the-art performance on POPE, MME, and four description-level hallucination benchmarks across LLaVA, MiniGPT-4, and Qwen2.5-VL. Code is available at https://github.com/zxp555/ACFT_MM
Multimodal large language models (MLLMs) struggle with fine-grained Visual Search, the task of locating small or rare objects in high-resolution images. Existing remedies fall into two families: (1) Training-free methods based on attention or confidence scores are accurate but slow, since they require multiple MLLM queries per example. (2) Reinforcement Learning (RL) trained tool-use models are faster at inference but opaque, since their tool calls remain uncontrollable and hard to interpret. To overcome this, we propose \emph{VisLens} (Visual Focus via Logit Lens), a Visual Search method built on the logit lens, which decodes the semantics held in a hidden state by projecting it through the LLM head. VisLens further uses a lightweight tuned-lens that maps early hidden states into the final hidden state space, so visual tokens can be read out from early layers. These tokens are matched to target words in the query to generate a crop of the relevant region, which is fed back in alongside the original image to produce the final answer. The whole process, from decoding to the final answer, completes in a single forward pass without repeated queries. VisLens matches or exceeds prior baselines while delivering a substantial latency advantage, running $8.5$--$9.9\times$ faster than Thyme and up to $22.2\times$ faster than training-free multi-pass search methods.
Multimodal Large Language Models (MLLMs) process speech and text jointly, yet whether they exploit prosodic cues for pragmatic inference or rely on surface acoustic patterns has received little systematic investigation. We address this through sarcasm detection, evaluating Qwen2.5-Omni and Qwen3-Omni on Mandarin Chinese and English under five modality conditions that decompose the contributions of lexical content, vocal semantics, and prosodic structure. Adding audio systematically inflates false positives without improving true positive detection. Acoustic error diagnosis reveals that model errors cluster on a shared stereotype of expressive prosody, namely elevated pitch and irregular pausing, that diverges from the actual cues marking sarcasm in both languages. Targeted manipulation of only these two dimensions causally confirms the heuristic, inducing false positive rates of up to 60%. Applying the same manipulation template to Gemini~3 Flash Preview without modification replicates the effect, suggesting that the stereotype extends beyond the Qwen Omni family rather than arising from a single model architecture.
External text can override conflicting image evidence in multimodal large language models, a failure we call multimodal contextual sycophancy. We introduce a 998-case diagnostic that independently varies visual evidence, commonsense priors, and external text, and probe when this failure arises by moving the information boundary around a context-blind visual witness. On abnormal images paired with Gemini-generated false text, GPT-5.1 scores 7.9% under joint conditioning, 49.7% when the context-blind witness report is scored directly, 63.7% under a matched two-call witness-arbiter pipeline that exposes the witness to the text, and 84.2% under System-2 Visual Arbitration (S2VA), which withholds the text from the witness. Across six models, S2VA improves over the direct witness report by 19.7 to 44.1 points, with all paired 95% confidence intervals excluding zero. The best information boundary is not uniform: textual context scaffolds some models, and a GPT-4o-regenerated subset changes the relative ordering of joint conditioning, Witness-Only, and S2VA. Contextual sycophancy is therefore sensitive to when text is introduced, as well as to the model and context source.
Aman Prakash, Sourish Dasgupta, Tanmoy Chakrabortycs.LG
Multimodal Large Language Models (MLLMs) can assign similar confidence to answers that fail for different reasons. We propose HalluPrism, a behavioral diagnostic that re-runs an answer after visual degradation, blank-image replacement, and grounding or relation checks. These targeted probes yield a signature over visual-perturbation sensitivity (V ), image-removal confidence retention (L), and grounding/relation-probe instability (A). Across 58K+ examples from four benchmarks and four MLLMs, image-removal confidence retention is most prevalent, while grounding/relation-probe instability better separates failure families. Only 18 of 48 source-target checks are diagonally aligned, so the coordinates should be interpreted jointly rather than as independent causal sources. With the dataset fixed, the joint signature improves failure-family AUROC from 0.634 to 0.769 on HallusionBench and from 0.707 to 0.817 on VizWiz, with smaller gains on POPE and VSR. In pooled XGBoost analysis, AUROC rises from 0.78 with scalar confidence to 0.95 with (V, L, A) and 0.97 when confidence is added. The same signature does not automatically improve correctness ranking. The three tested direct scalarizations can harm it. These results separate failure diagnosis from abstention scoring: multimodal uncertainty should characterize failure structure before it is used to decide whether to abstain or correct.
Hybrid attention dominates frontier LLMs, yet Vision Transformers (ViTs) in multimodal LLMs lack a satisfactory hybrid design, with no consensus on why certain attention patterns work better. To fill this gap, we study ViT attention heads and find they differentiate into object- and background-specialist roles, a pattern most pronounced under full attention; we call this Semantic Head Specialization (SHS). We propose SHS-Index to quantify this specialization, show that it distinguishes full-attention from chunk-window ViTs, and find that it strongly tracks downstream benchmark performance. We then identify three structural factors that shape SHS---window interaction, token serialization, and local softmax allocation---and use them as design principles for hybrid attention. Guided by these factors, we design Ariadne Attention, a hybrid that matches full attention on 22 image and video tasks at 6.5x less attention compute. Our findings establish head specialization as a measurable property for diagnosing and designing principled hybrid ViT attention at the multimodal-LLM scale.
Hanoona Rasheed, Haania Siddiqui, Ming-Hsuan Yang +2cs.CV
Spatio-temporal video grounding (STVG) requires models to identify when a referred event occurs and localize the target entity throughout that interval. Existing multimodal large language models typically serialize dense localization trajectories autoregressively, causing decoding latency to grow with tube length and allowing localization errors to propagate across time. We introduce Parallel Tube Decoding (PTD), a generative formulation that decomposes grounding into a temporal block followed by time-conditioned spatial blocks decoded simultaneously. This removes both token-level and trajectory-level dependencies, reducing the sequential decoding depth to a fixed $1 + 1$ rounds, independent of tube length. To enable parallel spatial generation, we introduce Decoupled Block Attention, which preserves access to shared video-query context while eliminating cross-box dependencies, together with localization-aware policy optimization for temporal boundaries and spatial geometry. On VidSTG, PTD reduces Tube Completion Latency by 79x and increases spatial decoding throughput by 92x over standard autoregressive decoding, while also improving grounding accuracy. With a compact 4B backbone, our model performs favorably well on VidSTG and HC-STVG, and generalizes zero-shot to temporal grounding, grounded VideoQA, and referring video object tracking. Our results show parallel tube generation is an efficient and effective alternative to autoregressive localization in videos.
In this paper, we propose a new token compression paradigm for video Multimodal Large Language Models (MLLMs), termed Visual Token Coding (VTC). Inspired by classical video coding principles, e.g., HEVC, VTC performs structured compression by predicting the I/P frames of a video and measuring their frame-wise residuals to estimate token redundancy. Based on this baseline framework, we also enhance VTC with a set of novel dynamic designs, such as Dynamic Resolution Input (DyRSO), Dynamic Token Allocation (DyTA), and Spatial Coverage Top-K (SC-TopK), and term this new approach $VTC_{Dy}$. To validate VTC, we apply it to three MLLMs and conduct experiments on multiple video understanding benchmarks. The experimental results show that VTC$_{\mathrm{Dy}}$ achieves an average performance retention of 100.1% with a 50% token budget for Qwen3-VL, while still retaining 97.8% of the average performance when the token budget is reduced to 25%. Moreover, as a plug-and-play design, VTC requires no additional tuning of MLLMs for token coding. Our code is available at https://github.com/Msr233/VTC.
Long-video understanding remains challenging for Multimodal Large Language Models (MLLMs) due to limited context length. Uniform sampling may miss crucial moments, while agent-based frame video understanding methods often evaluate frames independently, overlooking the temporal organization of videos. Ideally, evidence selection should mimic how humans answer questions about long videos: first locating the relevant segment from the global context, then zooming into local objects and details. We propose Temporal Tree of Thought T^3, a training-free framework for adaptive coarse-to-fine long-video understanding. T^3 constructs a question-agnostic hierarchical temporal tree via recursive temporally constrained clustering, where each node represents a contiguous segment with an informative key frame. During inference, T^3 performs an answer-retrieve-explore loop: it reasons over coarse representative frames, generates a search statement when evidence is insufficient, and expands relevant branches for finer-grained evidence. This process adaptively shifts the search target from temporal regions to specific objects and visual details to help video understanding. Experiments on VideoMME, LongVideoBench, and LVBench show that T^3 improves Qwen2.5-VL-7B by 0.5%, 4.6%, and 4.4%, respectively, under the same frame budget, demonstrating the effectiveness of structured temporal reasoning.
Recent advances in Multimodal Large Language Models (MLLMs) have extended Image Aesthetic Assessment (IAA) beyond scalar scores toward interpretable critique and guidance. Yet existing benchmarks mainly assess intrinsic visual quality or fixed domain criteria, leaving open whether an appealing image is appropriate for a specific purpose, audience, cultural setting, or domain convention. We introduce AesCanvas, a unified suite with two complementary components: CritiqueCanvas with 519,136 instruction-response pairs from 54,300 images supports long-form, multi-dimensional critique across photography, painting, and virtual imagery, whereas ContextCanvas with 301 expert-reviewed use scenarios evaluates contextual aesthetic suitability in realistic use scenarios. Under a unified protocol, we evaluate closed-source frontier, open-weight general, and aesthetic-specific MLLMs. Results reveal a clear separation between critique generation and context-sensitive judgment: reference-based lexical and semantic metrics only partially capture critique quality, while aesthetic specialists remain competitive on selected critique metrics yet substantially lag strong general-purpose MLLMs on ContextCanvas. Further analyses show that aesthetic specialization does not reliably transfer to contextual suitability and that model decisions may fail to track or ground themselves in decisive contextual visual cues. These findings establish culturally situated, evidence-grounded suitability as a distinct objective for aesthetic modeling.
Recent large language models achieve strong performance on complex reasoning tasks, where reinforcement learning with Group Relative Policy Optimization (GRPO) has emerged as a leading paradigm for optimizing models on self-generated trajectories. However, the on-policy nature of GRPO bounds the model to the reasoning skills it can already produce, restricting to learn more advanced capabilities. Prior works inject privileged reasoning traces from a stronger teacher policy to guide training, yet these traces are inherently out of distribution with respect to the student policy. We observe that this mismatch between on-policy and off-policy causes gradient clipping on semantically critical reasoning tokens, ultimately rewarding correct answers while leaving the reasoning that justifies them unlearned. Hence, we propose \textbf{Echo-GRPO}, a framework that lets the model reason in the words it speaks. Rather than imitating low-probability privileged traces from the teacher model, Echo-GRPO rewrites them into the student policy's own \textit{idiolect}, that is, its own characteristic vocabulary and expression patterns, while preserving their semantics via Dual-Reference Decoding. We instantiate this framework as \textbf{VideoEcho-R1} for video reasoning distillation, achieving consistent improvements across three multimodal LLM backbones and five benchmarks. Finally, we show that our idiolectal paraphrasing is a plug-in module that consistently improves both RL and supervised fine-tuning frameworks for reasoning distillation, demonstrating that policy-aligned supervision extends beyond GRPO.
Multimodal large language models (MLLMs) are increasingly capable scientific assistants, yet they remain far from fully autonomous research. This transition requires models to actively inspect academic papers, build global evidence views, and make traceable judgments without prespecified issues or evidence. However, existing work provides limited task paradigms or training studies for such issue- and evidence-absent verification. We study this challenge through scientific error detection, where models must determine whether errors exist and justify them with evidence-based reasoning. To fill this gap, we present VERA-RL, a reinforcement-learning formulation for scientific error detection over academic papers. Following a Reason--Verify--Scan progression, we construct VERA-13K, a 12,900-sample dataset organized into 4,300 matched chains, covering 6 scientific-error categories across the research workflow and broad natural-science domains. We further introduce fine-grained rewards for reasoning completeness, evidence alignment, and error precision. Training Qwen3-VL-8B with VERA-RL substantially improves verifiable reasoning, approaching flagship MLLMs such as Gemini 3 Pro and Qwen3-VL-235B-A22B on Scan.
In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU-CPT), enabling deployed MLLMs to continually evolve from streaming unlabeled data. Existing unsupervised post-training methods for MLLMs typically optimize target tokens uniformly, overlooking their heterogeneous visual dependence (VD). However, we reveal that token-level VD is crucial for MU-CPT. Specifically, its structural distortion serves as an indicator of cross-modal catastrophic forgetting, and its inherent heterogeneity acts as a compass to guide new-task learning. Leveraging this property, we propose a Visual Dependence-Aware (VDA) framework with two main components. First, Visually Constrained Optimal Transport (VC-OT) formulates the VD structural distortion of old-task VD during new-task learning as an optimal transport problem to mitigate cross-modal forgetting. By designing a region-aware ground cost and a dependence-stratified transport penalty, it prevents global shifts in visual focus while strictly prohibiting visual reliance from degenerating into language bias. Second, Visually Modulated Adaptation (VMA) exploits VD heterogeneity to emphasize visually grounded new-task learning, promoting new-task plasticity. Together, our method simultaneously maintains old-task stability and new-task plasticity during challenging MU-CPT. Extensive experiments under our MU-CPT setting validate the effectiveness of VDA.
Reliable underwater perception requires complementary sensing under variable visibility. Optical cameras capture appearance and semantics but degrade rapidly with turbidity, whereas imaging sonar preserves geometry while exhibiting distinct range-azimuth structure and acoustic artifacts. Existing MLLMs, built primarily on optical encoders, are therefore ill-suited to model sonar or adaptively exploit sonar-optical complementarity. We propose SonarLLM, a sonar-optical MLLM that treats sonar as a native perceptual modality. It combines a sonar-specific encoder, modality-specific physics-aware feature enhancement, and reliability-aware hierarchical fusion to align acoustic structure with optical semantics and dynamically adjust their contributions as sensing quality changes. We also introduce SonarBench, a paired benchmark that spans four tasks: recognition, counting, visual question answering, and captioning; and, across the benchmark, three input settings: sonar-only, optical-only, and fusion. By fixing the scene and sonar observation while varying optical degradation, SonarBench enables controlled measurement of cross-modal complementarity. SonarLLM achieves 72.0% macro accuracy across sonar-only recognition, counting, and VQA, outperforming the strongest baseline by 34.4 percentage points, and 68.7% under fusion, exceeding the best baseline by 25.1 points. For recognition and counting, the fusion-over-optical gain grows from 6.0 to 36.0 points as turbidity increases, indicating the increasing complementary value of sonar under controlled optical degradation. Together, these results show that robust heterogeneous perception depends not only on adding sonar, but on representing and weighting it according to its sensing characteristics.
Inferring the collective emotional state of a group of people from a single image, a task known as group emotion recognition (GER), requires integrating spatially distributed cues such as faces, poses, interactions, and scene context. Current methods rely on detector-driven multi-stream pipelines. These are trained with only image-level supervision that lacks guidance on which regions matter or how strongly each contributes. We propose LG-GER, a language-guided distillation framework that uses a multimodal large language model (MLLM) to generate dense, spatially grounded evidence, i.e., bounding boxes paired with emotion signals and confidence scores, for the training images. This structured evidence is distilled into a single vision-language model (VLM) backbone through four complementary losses: classification, region-text grounding, spatial emotion, and spatial confidence regression. At inference, LG-GER requires no detectors, no MLLM, and no multi-stream fusion, making GER practical for real-time and resource-constrained deployment. LG-GER has been evaluated on two benchmark GER datasets (GroupEmoW and GAF~3.0) and achieves competitive or superior results compared to state-of-the-art methods that require detection and multi-stream processing at inference.
Frontier multimodal large language models (MLLMs) deliver impressive perception yet still falter on scientific and mathematical reasoning. Parameter-level adaptation is unavailable for closed-weight or on-device backbones, and stateless prompting forfeits any compounding benefit from problems already solved. We propose \textbf{DG-Mem}, a dual-grained agentic memory framework that augments a frozen MLLM with a non-parametric, externally stored memory built once from training-time rollouts and consulted read-only at test time. Motivated by the Complementary Learning Systems (CLS) account of human memory, DG-Mem factors its store into an instance-grounded exemplar memory and a category-level schema memory of IF-THEN rules, with a transient reflection store mediating their construction so that schemas are synthesized only from abstract reflections, never from exemplar text. Two design choices distinguish DG-Mem: an online concept categorizer that grows the category space incrementally during training rather than committing to a predefined taxonomy, and a Shapley context attribution procedure that decomposes correctness across the entire retrieved rule set and yields a per-rule utility that re-weights retrieval at test time. The pipeline introduces no gradient updates and is deployable on closed-weight or on-device backbones. Across MathVista, MMMU, and MMMU-Pro on four open-weight and proprietary backbones (Qwen3.5-27B, Qwen3.5-122B-A10B, GPT-5-Nano, Gemini-3-Flash), DG-Mem improves consistently over no-memory and competitive memory baselines.
Multimodal large language models (MLLMs) achieve strong performance on VQA and scene understanding, yet affective reasoning remains vulnerable to shortcut behavior. Models may predict correct answers while neglecting people-centric cues such as micro expressions and body language, which weakens traceability and external verification. Prior reinforcement learning approaches mainly reward context or logical coherence without explicitly enforcing attention to human evidence. In addition, LLM as a Judge scoring often suffers from score clustering, which reduces reward discriminability. We propose AffectOmni, a GRPO trained framework for verifiable affective reasoning. AffectOmni introduces People Focus and Temporal Order rewards to encourage people-centric evidence selection and temporally structured reasoning, and it adopts within-group comparative scoring to produce more stable and discriminative reward signals. For verification, a Thinking Summarizer converts free form rationales into executable evidence instructions, which are grounded into pixel level evidence regions via SAM3 to provide an externally auditable interface outside the training loop. Experiments on IntentBench, Daily Omni, and WorldSense show consistent improvements over open source 7B scale baselines, including gains of 4.66% on emotion recognition and +14.29% on temporally sensitive tasks. Code is available at https://github.com/eliot127825-rgb/AffectOmni_nobody.
Unified models for visual understanding and generation have made rapid progress, yet they still lack the ability to understand and manipulate the spatial states of object instances. Existing models can describe objects in natural language, but they struggle to precisely represent continuous object poses and generate geometrically consistent images under target viewpoints. To mitigate this, we propose \emph{Object-Uni}, a unified model for object-centric spatial understanding and controllable generation. Specifically, we formulate object-centric spatial intelligence as a unified problem connecting pose perception, spatial reasoning, pose-conditioned generation, and object-centric novel view synthesis. We treat object pose as an explicit geometric variable shared by understanding and generation, rather than merely a prediction label or control signal. To make pose usable by multimodal large language models, we propose a viewpoint-based orientation abstraction that maps orientation into structured viewpoint descriptions while preserving continuous geometric supervision. We further construct an object-centric spatial benchmark (UniSpatial-80K) and train a unified model with an object-token-grounded pose anchor to associate each instance with its pose state. Experiments show that our model improves object-level pose understanding and pose-controllable generation, moving unified models from describing objects toward manipulating spatial states.
Diffusion multimodal large language models (dMLLMs) frequently produce long-form outputs marred by semantic drift and repetition, with quality generally degrading as output length increases. We identify two structural deficiencies in existing decoding methods as primary drivers of these failures: confidence-based scoring ignores decoded-neighbor support, and block partitioning prevents access to high-readiness semantic anchors, together causing tokens to be committed before their local context is sufficiently established. We propose \ours{} (\textbf{C}ontext-\textbf{A}ware \textbf{C}luster \textbf{D}ecoding), a training-free decoding method that scores each masked position by a multiplicative composite of softmax confidence and neighbor proximity, promoting contextually ready tokens above isolated candidates while suppressing low-confidence positional noise, operating block-free to keep high-readiness anchors globally accessible. \ours{} further applies architecture-aware calibration to handle confidence heterogeneity induced by diverse visual integration strategies. Experiments on three dMLLMs across four benchmarks demonstrate consistent quality gains and hallucination reduction over Original, with larger gains in several longer generation settings, highlighting the importance of neighbor support and visual integration strategy for future dMLLM decoding method design. Our code is openly available at https://github.com/zhaoyk-sysu/CACD-dMLLM.
Chenghua Zhu, Zhaolu Kang, Qifan Shi +8cs.CV cs.CL cs.LG
Video multimodal large language models have advanced significantly, yet fine-grained motion-temporal understanding remains fragile. The core bottleneck is not only sparse frame sampling, but also the lack of a complete temporal modeling pipeline for explicitly representing frame-to-frame change, enabling appearance-motion interaction, and optimizing temporal direction sensitivity. We propose COMET, a temporally grounded framework that systematically strengthens video MLLMs through explicit temporal representation, appearance-motion fusion, and direction-aware optimization. Architecturally, COMET introduces a temporal motion branch built on Taylor frame differences and injects its motion evidence into the appearance stream via temporal attention bias-enhanced cross-attention. For optimization, COMET combines temporal prior distillation with a forward-reverse TC-GRPO stage that turns temporal order into a direct learning signal and strengthens the model's use of directional motion patterns encoded by the temporal motion branch. The method achieves consistent overall improvements with a pronounced motion-temporal bias: on Qwen3-VL-8B, action-centric tasks (STAR, SSv2) improve by 4.9% on average, temporal reasoning tasks (NExT-QA, CLEVRER, LLaVA-178K) by 2.1% over BL-GRPO, while static perception tasks (PerceptionTest) remain on par. The same gain pattern also transfers to InternVL2.5-8B, indicating that COMET generalizes across model families.
Multimodal LLMs apply the language model interface to visual inputs, where ordinal regression tasks such as age estimation, image quality assessment, and disease grading require autoregressive decisions over ordered class labels. We ask whether MLLMs reliably convert internal ordinal evidence into ordered digit-token outputs. Across four ordinal benchmarks and four MLLM backbones, ordinal labels are linearly recoverable from hidden states with Spearman correlation up to 0.938, and a task-designed prompt further sharpens this structure. Yet native digit-token outputs weakly expose it: the unembedding matrix filters the ordinal direction, and the digit-token row space retains below 1.15% across all 16 model-dataset combinations, with a 16 to 77 absolute-point accuracy gap between linear-probe and native outputs. We introduce Ordinal Lens Alignment (OLA), a frozen-backbone inference-time method that trains lightweight W_S-anchored lenses on mid-to-deep decoder layers, fuses them into an ordinal distribution, and corrects only digit-token logits at generation. OLA outperforms the SOTA LoRA-tuned OrderChain baseline in most settings while keeping the MLLM frozen, surpasses discriminative ordinal baselines in most cells, and improves over an offline lens in every setting.
Multimodal harmful meme detection is typically formulated as image--text harmfulness classification. A model may correctly predict harmfulness while misidentifying the attacked target or its supporting evidence. We therefore extend harmful meme detection with fine-grained target identification, asking what type of target is attacked, who is targeted, and where the target appears in the meme. The model predicts harmfulness for every meme and, for harmful memes, outputs the target category, target entity, textual mention, and visual region. To support this task, we introduce Meme3W, which unifies multiple public harmful meme datasets and provides human-verified annotations for harmful instances. We further introduce Joint Record Accuracy (JRA), a strict record-level metric requiring the harmfulness label and all target-identification fields to be jointly correct. Experiments with representative multimodal large language models reveal a substantial gap between harmfulness accuracy and JRA. To narrow this gap, we propose HarmTrace, an anchor-calibrated decoupled optimization framework. HarmTrace strengthens target-entity supervision through entity-aware supervised fine-tuning. It then applies Conditional Target-identification Policy Optimization (CTPO) to decouple harmfulness and target-identification advantages, restricting target-identification optimization to label-correct responses for harmful examples. CTPO uses a Virtual Positive Anchor (VPA) as a fully correct reference for target-identification advantage normalization. HarmTrace improves both JRA and harmfulness accuracy across the evaluated backbones, with JRA on the Qwen3-VL-8B backbone increasing from 17.58\% to 52.51\%. Our code is publicly available at https://github.com/llly1234/HarmTrace-for-Harmful-Memes.
Frame selection is a fundamental component of multimodal large language models, enabling long videos to be processed under limited visual-token and computational budgets. Uniform sampling preserves temporal coverage but may miss informative content that appears only briefly. To alleviate this limitation, query-dependent methods can retrieve question-relevant frames. However, because the selected frames depend on the current question, the same visual input cannot be directly shared across different questions, and frame selection must be repeated in multi-turn video dialogue. This motivates us to seek a query-independent frame selection method that preserves the reusability of a fixed visual input while improving the coverage of informative events beyond uniform sampling. We propose Multi-Signal Event Modeling and Dynamic Rescoring (MEDR), a training-free and query-independent frame selection method. Multi-Signal Event Modeling organizes complementary visual, motion, and text signals into signal-specific temporal events. Dynamic Rescoring then iteratively reevaluates each candidate relative to the current selected set, updating its score according to frame-level signal strength, additional event coverage, and temporal proximity. The resulting fixed frame set is constructed without observing the query and can be reused across different questions. On the standard benchmark evaluations, MEDR improves model accuracy by 0.63%-0.89% on Video-MME. On the long-video subset of LongVideoBench, it improves accuracy by up to 1.23% with Qwen3-VL-8B. MEDR further improves overall accuracy by 0.53%, while reusing exactly the same frame set for every question about a video.
Interpreting the emotional responses triggered by images is central to achieving emotional intelligence. Compared with natural images, visual art is intentionally created to elicit emotional responses from its viewers through abstract concepts and visual metaphors, making affective interpretation particularly challenging. However, most existing methods rely on general-purpose visual embeddings (e.g., CLIP), failing to capture the nuanced cues underlying artistic emotion. To address this gap, we propose \textbf{ProFocus}, a novel framework that models affective experience in artistic images via progressive visual focusing. The key idea is to model visual representation learning inspired by a hierarchical cognitive theory of human aesthetic appreciation. Technically, ProFocus contains two core components: a Hierarchical Art Critic (HAC) and a Progressive Hint Fusion (PHF) module. HAC leverages multimodal large language models to generate structured linguistic priors at three cognitive levels--atmospheric style, narrative subjects, and concrete details--thereby translating artistic perception into coherent semantic guidance. Building upon these priors, PHF departs from conventional cross-modal fusion by sequentially injecting the hierarchical hints into visual features, enabling a progressive focusing process that mirrors human perception. This design allows the model to capture subtle affective cues and produce more faithful explanations. Extensive experiments on the ArtEmis v1.0 and v2.0 datasets demonstrate that ProFocus consistently outperforms state-of-the-art methods in both emotion recognition and affective explanation. Project page: https://github.com/Zhang-Zhiyan/ProFocus.
Xinming Wang, Weinong Wang, Hongming Yang +13cs.CV
Hybrid-thinking multimodal large language models (MLLMs) allow a single model to alternate between deliberative thinking and latency-efficient non-thinking inference. Although these modes differ in reasoning budget, their delivered responses should satisfy the same user-facing standard. Correctness alone may not characterize this response quality; we therefore evaluate task accuracy and response-pattern failures as complementary outcomes. We study this gap through \textbf{response-pattern alignment}: whether thinking and non-thinking interfaces preserve acceptable final-response behavior. We introduce \textbf{PatternEval}, a failure-enriched diagnostic benchmark comprising 2,415 multimodal prompts spanning visual perception and grounding, structured image understanding, and multimodal knowledge reasoning. PatternEval tests four recurrent failures: chain-of-thought leakage, response repetition, logical contradiction, and performative reasoning. Response-pattern failures are widespread across models from different providers, with non-thinking inference exhibiting substantially higher failure rates and thereby creating systematic misalignment between thinking and non-thinking interfaces. Motivated by this diagnosis, we develop \textbf{PatternRM}, a response-level reward model, and \textbf{PatternRL}, which introduces pattern-specific penalties during reinforcement learning. Experiments on Qwen3-VL-4B and Qwen3-VL-8B show that incorporating pattern-specific penalties into reinforcement learning can mitigate cross-mode misalignment while incurring a marginal task performance trade-off. Together, PatternEval and PatternRL provide an evaluation-and-training framework for aligning user-visible response patterns across hybrid-thinking interfaces.