Paper Archive

Cheng-Yu Yang, Shao-Yuan Lo, Yu-Lun Liu 6/10/2026 arxiv

Vision-language models (VLMs) project images into hundreds to thousands of visual tokens, making decoder inference expensive in both attention computation and KV-cache memory. Existing visual-token reduction methods largely follow a rank-and-remove paradigm: they score visual tokens, keep a compact ...

Yeongseo Jung, Jaehyeok Kim, Eunseo Jung, Jiachuan Wang, Yongqi Zhang, Ka Chun Cheung, Simon See, Lei Chen 6/10/2026 arxiv

Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with conversation length. Naive truncation or summarization degrades fidelity, while existing context compressors lack cross-turn memory sharing or revi...

Kian R. Weihrauch, Thomas A. Buckley, William Lotter, Arjun K. Manrai 6/10/2026 arxiv

General-purpose large language models (LLMs) are routinely used as baselines when evaluating specialized pathology models on whole-slide images (WSIs). Because WSIs exceed contemporary model context limits, LLM baselines routinely use small, high-magnification patches processed independently via maj...

Steven Oh, Jason Jingzhou Liu, Tony Tao, Philip Han, Kenneth Shaw, Satoshi Funabashi, Ruslan Salakhutdinov, Deepak Pathak 6/10/2026 arxiv

Contact-rich manipulation requires force sensitivity, but many robot arms lack dedicated force sensors due to their high cost. We present Neural External Torque Estimation (NEXT), a data-driven method that estimates external joint torques without needing any dedicated force sensors. NEXT trains in 1...

Zefu Lin, Rongxu Cui, Junjia Xu, Xiaojuan Jin, Wenling Li, Lue Fan, Zhaoxiang Zhang 6/10/2026 arxiv

Vision-Language-Action (VLA) models inherit semantic grounding from large-scale pretraining and perform competently across in-distribution manipulation tasks. This grounding, however, is built on static image-text pairs, whereas manipulation is a continuous, contact-rich process whose dynamics this ...

Jadelynn Dao, Milan Ganai, Yasmina Abukhadra, Ajay Sridhar, Mozhgan Nasr Azadani, Katie Luo, Clark Barrett, Jiajun Wu, Chelsea Finn, Marco Pavone 6/10/2026 arxiv

Vision-Language Models (VLMs) are increasingly deployed as high-level planners for embodied agents, with an emerging strategy of scaling test-time compute to improve capability. However, we observe that doing so increases latency, token usage, and FLOPs while yielding uneven, often diminishing gains...

Xingjian Diao, Wenbo Li, Yashas Malur Saidutta, Avinash Amballa, Lazar Valkov, Srinivas Chappidi 6/10/2026 arxiv

Long input sequences are central to document understanding and multi-step reasoning in Large Language Models, yet the quadratic cost of attention makes inference both memory-intensive and slow. Context distillation mitigates this by compressing contextual information into model parameters, and recen...

Songhao Wu, Ang Lv, Ruobing Xie, Yankai Lin 6/10/2026 arxiv

Router is the cornerstone component to the Mixture-of-Experts models. Serving as expert proxies, the rows of the router matrix compute their similarity to the MoE inputs to determine which subset of experts is activated. Ideally, each router row is designed to encode the expert matrix into this repr...

Jin Yao, Dhruva Dixith Kurra, Tom Lampo, Zezhou Cheng, Danhua Guo, Burhan Yaman 6/10/2026 arxiv

Vision-language-action (VLA) models can describe scenes and reason about them in language, yet still struggle to ground their actions in the dense 3D world around them. Existing approaches either inject features from a frozen 3D foundation model without an objective that ensures the policy uses them...

Haotao Xie 6/10/2026 arxiv

Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry. However, domain-specific research on precise translation and affective-semantic understanding of classical poetry remains limited. The main c...