Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generation timesteps. Through token-importance probing, we identify an asymmetric core-expansion structure: understanding exhibits a stable importance component, while generation largely shares this component but requires progress-dependent corrections. We therefore propose CE-Router, which uses a task-shared core scorer and progress-conditioned generation expansions, optimized through generation decomposition and cross-task core alignment. At inference, CE-Router compacts token computation and supplies a learned routing signal to Unified Computation Scheduling, which coordinates layer skipping, FFN pruning, diffusion-head cache reuse, and denoising-step early exit. Experiments on two representative UMM architectures demonstrate consistent quality--efficiency improvements across both tasks, retaining 98.03\% of dense understanding performance with a 1.93$\times$ end-to-end inference speedup.
Sai Krishna Arthanari, JaeHyeong Chang, Chengzhe Sun +1cs.CL
Efficient-transformer research often motivates token pruning and adaptive computation with the claim that not all tokens require equal computational effort. We test this claim end to end using SEWN, a two-stream Transformer that routes tokens through either lightweight or full-capacity processing using a learned gate. Across our experiments, routing introduces negligible accuracy change relative to parameter-matched baselines, while the gate's token-importance signal depends critically on how it is learned. A static lexicon-seeded prior fails a counterfactual faithfulness test on BoolQ, whereas a fully contextual gate achieves highly significant separation ($p<10^{-10}$) on both evaluated tasks without changing task accuracy.
Full self-attention is a strong token mixer for PDE surrogates on irregular domains, but its quadratic cost limits its use on high-resolution problems. Efficient latent-attention models such as the Fast Low-rank Attention Routing Engine (FLARE) avoid that cost by routing all N tokens through M << N learned latent queries, but those queries are parameters: once trained, the same learned query templates serve every input. We remove this restriction with FLARE++, a low-rank attention architecture with dynamic token routing. FLARE++ reuses FLARE's own encoder to build its routing queries: learned latent seeds drive one extra encode call that gathers the N input tokens into M input-conditioned queries, and those queries then determine how the same tokens are compressed and redistributed. This preserves FLARE's explicit low-rank factorization and linear O(NM) complexity, and expresses the complete routing operation with standard scaled dot-product attention (SDPA) calls alone. We also provide a multi-GPU context-parallel implementation that shards input tokens across devices without ever gathering the full token sequence on one of them. FLARE++ is competitive across a set of standard PDE surrogate benchmarks, improving on fixed-query FLARE by 24% on average, and it gains 2.3 points of average accuracy on Long Range Arena.
Vision-language models commonly project all tokens produced by a pretrained vision encoder into a large language model. However, final-layer features can discard text, local attributes, and spatial relationships, while high-resolution inputs substantially increase context length and inference latency. We introduce \method, a Multi-scale Adaptive Vision Encoder. \method uses position-dependent gates to fuse shallow, intermediate, and deep features from a vision Transformer, preserving global semantics while enhancing edges, text, and local structure. It then performs question-conditioned token routing according to question relevance, local information content, global semantics, and spatial coverage, with a token budget that adapts to image complexity. To mitigate compression loss, we further introduce full-to-compressed representation distillation and a spatial diversity regularizer. In an illustrative simulation under a unified 7B language-model framework, \method reduces the average number of SigLIP-SO400M visual tokens from 729 to 146 (approximately 80.0\%) and improves the mean score on VQAv2, GQA, TextVQA, ScienceQA-IMG, and MMBench by 2.2 percentage points, while reducing single-image time to first token from 228\,ms to 129\,ms. We provide the full model design and evaluation protocol. All reported numbers currently serve only as placeholders for paper organization and experimental design; formal claims require real training runs, independent replications, and official benchmark evaluation.
Perineural invasion (PNI) is associated with poor postoperative outcomes in intrahepatic cholangiocarcinoma, but it is confirmed by surgical pathology. Existing preoperative imaging models often rely on radiologist-defined variables, contrast-enhanced imaging, or manual annotations. We propose an anatomy-privileged teacher--student framework for patient-level PNI prediction from T2-weighted MRI. During training, the teacher uses MRI with tumor and liver masks to learn dense token routing, and the student distills this guidance to retain and aggregate informative tokens under a fixed budget. Anatomical supervision is restricted to training, and the deployed model does not require masks at inference. In 155 patients, the proposed method achieved the highest mean AUROC of 0.750 among matched MRI-only baselines evaluated under the same protocol, with 1.43 GFLOPs and 8.02 ms per case on a Jetson Orin Nano Super Developer Kit.
Efficient inference in Large Language Models (LLMs) requires deciding where computation can be reduced while preserving model quality. We study this problem through multilayer perceptron (MLP) activation sparsification and token-level conditional routing. We first propose Sensitivity-Aware Thresholding for Sparsity (SATS), a threshold calibration method to choose layerwise gate thresholds using a local MLP output sensitivity proxy rather than calibrating thresholds directly from activation percentiles. While SATS retains the existing mechanism of sparsifying MLP activations by thresholding gate activations, it replaces percentile-based calibration with a sensitivity-aware selection rule. We then introduce a lightweight token routing framework that dynamically selects between a base path and a modified path on a per-token basis, rather than applying the modified computation uniformly to all tokens. We evaluate both methods on multiple recent open-weight LLMs. Our results show that SATS improves over the threshold-based sparsification baseline at matched actual sparsity and that token routing yields a more favorable quality-throughput trade-off than static activation modification baselines. Overall, our results suggest that improved threshold calibration and token routing can improve the quality-throughput trade-off in LLMs.
Multimodal large language models (MLLMs) commonly inherit the deep, symmetric Transformer backbone designed for unimodal text modeling, and apply the same computation uniformly to image and language tokens. This design overlooks a key modality asymmetry: image and text tokens differ substantially in information density, redundancy, and required reasoning depth. Through a layer-wise analysis of LLaVA-1.5, we observe that vision tokens tend to saturate in the middle layers. Specifically, text-to-image attention decreases from 0.68 at layer 0 to 0.07 by layer 4, and stabilizes near 0.04 after layer 18, whereas text tokens continue to benefit from deep semantic processing. These findings suggest a mismatch between architectural symmetry and depth-asynchronous modality evolution, resulting in redundant visual computation and possible drift in perceptual representations during deep task-specific adaptation. Motivated by this, we propose Dual-Path Vision Token Routing (DPVR), a modality-asymmetric routing framework for efficient MLLMs. Its core instantiation, DPVR-LF (Late-Layer Fusion), routes vision tokens at the saturation point into a one-layer trainable side branch, runs a thirteen-layer text-only forward that skips image positions in the deep stack, and re-fuses the visual and textual streams only at the final layer. With approximately 3% trainable parameters, DPVR-LF preserves competitive multimodal performance on standard benchmarks while reducing visual computation in the deep Transformer stack. The results challenge the conventional assumption that vision tokens must traverse all deep language-model layers, and indicate that a single late fusion layer can be sufficient for maintaining strong perceptual competence in LLaVA-style MLLMs.