collaborators

5 papers

cs.AI2026

Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context Prefilling

Yujie Chen, Tailai Chen, Yifeng Gao +4

Prefilling computational costs pose a significant bottleneck for Large Language Models (LLMs) and Large Multimodal Models (LMMs) in long-context settings. While token pruning reduc…

cs.CV2026

FoodSense: A Multisensory Food Dataset and Benchmark for Predicting Taste, Smell, Texture, and Sound from Images

Sabab Ishraq, Aarushi Aarushi, Juncai Jiang +1

Humans routinely infer taste, smell, texture, and even sound from food images a phenomenon well studied in cognitive science. However, prior vision language research on food has fo…

cs.RO2026

HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models

Zixing Chen, Yifeng Gao, Li Wang +8

Vision-Language-Action (VLA) models inherit rich world knowledge from vision-language backbones and acquire executable skills via action demonstrations. However, existing evaluatio…

cs.CL2026

SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation

Gengyang Li, Wang Cai, Yifeng Gao +1

Chain-of-Thought (CoT) prompting improves reasoning but often produces long and redundant traces that substantially increase inference cost. We present SyncThink, a training-free a…

cs.CL2025

ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy

Gengyang Li, Yifeng Gao, Yuming Li +1

While Chain-of-Thought (CoT) prompting improves reasoning in large language models (LLMs), the excessive length of reasoning tokens increases latency and KV cache memory usage, and…