activity
20242026
collaborators

34 papers

cs.CV2026

VEGAS: Human-Aligned Video Caption Evaluation via Gaze

Shenghui Chen, Po-han Li, Ximeng Sun +5

Vision-language models excel at video captioning, yet typically generate descriptions that fail to capture individual viewers' attention. We propose VEGAS (Video caption Evaluation…

cs.CV2026

Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion

Shivam Singh, Saptarshi Majumder, Pratik Prabhanjan Brahma +2

Recent Vision-Language Models (VLMs) struggle with grounded reasoning, temporal consistency, and context aware planning in videos. We introduce pause-and-think-T, a reasoning-centr…

cs.LG2026

PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning

Daize Dong, Junlin Chen, Haolong Jia +9

Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement learning (RL) on MoE-based LLMs often suffers from training instab…

cs.CV2026

DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning

Chao Huang, Zeliang Zhang, Jiang Liu +7

Multimodal large language models (MLLMs) have made rapid progress, yet their reasoning ability often lags behind strong text-only LLMs. Bridging this gap typically requires large-s…

cs.CL2026

AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection

Pretam Ray, Pratik Prabhanjan Brahma, Zicheng Liu +1

Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large language models (LLMs) during inference.…

cs.CV2026

CaptionQA: Is Your Caption as Useful as the Image Itself?

Shijia Yang, Yunong Liu, Bohan Zhai +5

Image captions serve as efficient surrogates for visual content in multimodal systems such as retrieval, recommendation, and multi-step agentic inference pipelines. Yet current eva…