16 citations · 17 across the 12 of their papers we have counts for
16 papers
Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
Songze Li, Haoming Gu, Ziyang Gong +11
Vision-language navigation requires agents to follow natural-language instructions to reach target locations, making high-quality language supervision essential. Since human annota…
Draft-KV: Learning Useful Latent Communication Between Language Models
Linquan Wu, Shichang Meng, Tianxiang Jiang +7
Latent communication passes internal states between language models instead of decoded text, but higher receiver accuracy does not show that the receiver used the message content.…
What Should a Self-Teacher See? Privileged Context Design for On-Policy Self-Distillation
Kanghui Tian, Siyuan Liu, Tianxiang Jiang +8
More privileged information does not always make a better teacher. We study this tension in on-policy self-distillation (OPSD), where a self-teacher scores the student's own rollou…
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
Yuhan Zhu, Changlian Ma, Xiangyu Zeng +12
Video multimodal large language models (MLLMs) can describe what happens in a video, but rarely identify when the supporting evidence occurs. We study generalist video temporal gro…
SER: Learning to Ground Video Reasoning with Semantic Evidence Rewards
Sheng Xia, Zhengqin Lai, Tianxiang Jiang +4
Video MLLMs often struggle with fine-grained spatio-temporal reasoning, sometimes generating correct answers based on irrelevant frames or objects. Although outputting spatio-tempo…
InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning
Ziang Yan, Sheng Xia, Jiashuo Yu +10
Recent progress in foundation models has shifted toward agentic behavior involving multi-step reasoning and tool use. However, open-source efforts largely focus on text-dominant se…
Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction
Tianxiang Jiang, Linquan Wu, Sheng Xia +5
Video event prediction (VEP) requires models to infer unobserved future states from partial video evidence. Existing video MLLMs usually verbalize intermediate future reasoning in…
RIVER: A Real-Time Interaction Benchmark for Video LLMs
Yansong Shi, Qingsong Zhao, Tianxiang Jiang +3
The rapid advancement of multimodal large language models has demonstrated impressive capabilities, yet nearly all operate in an offline paradigm, hindering real-time interactivity…
Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning
Xiangyu Zeng, Zhiqiu Zhang, Yuhan Zhu +12
Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting their ability to identify sparse y…
LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
Linquan Wu, Tianxiang Jiang, Yifei Dong +6
Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamics. In this work, we identify a critica…
VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
Tianxiang Jiang, Sheng Xia, Yicheng Xu +5
While Multimodal Large Language Models (MLLMs) have become adept at recognizing objects, they often lack the intuitive, human-like understanding of the world's underlying physical…
ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
Yicheng Xu, Yue Wu, Jiashuo Yu +9
Multimodal Large Language Models (MLLMs) hold promise for accelerating scientific discovery by interpreting complex experimental procedures. However, their true capabilities are po…
FaceSleuth-R: Adaptive Orientation-Aware Attention for Robust Micro-Expression Recognition
Linquan Wu, Tianxiang Jiang, Haoyu Yang +5
Micro-expression recognition (MER) has achieved impressive accuracy in controlled laboratory settings. However, its real-world applicability faces a significant generalization clif…
Make Your Training Flexible: Towards Deployment-Efficient Video Models
Chenting Wang, Kunchang Li, Tianxiang Jiang +3
Popular video training methods mainly operate on a fixed number of tokens sampled from a predetermined spatiotemporal grid, resulting in sub-optimal accuracy-computation trade-offs…
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
Xiangyu Zeng, Kunchang Li, Chenting Wang +10
Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in short video understanding. However, understanding long-form videos still remains challenging fo…
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
Yi Wang, Kunchang Li, Xinhao Li +17
We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialog…