10 papers
DualAffect: Dual-Path Paralinguistic Integration for Generative Audiovisual Emotion Understanding
Yibo Wang, Jisheng Dang, Bimei Wang +8
Understanding human emotion is essential for multimodal systems that interpret both the content of an interaction and the speaker's expressive state. However, connecting paralingui…
DNAlign: Dynamic Null-Space Safe Alignment for LLMs
Jisheng Dang, Yushuo Zhao, Dewei Liu +6
Ensuring the safe and reliable deployment of large language models (LLMs) remains a fundamental challenge. Existing safety alignment approaches either incur high computational cost…
PhysMLLMs: Spatial Priors for Unified Referring Segmentation and Grounded Reasoning of Images and Videos
Siyao Yan, Bo Han, Jisheng Dang +7
Video multimodal large language models support language guided video segmentation, but they often show spatio temporal inconsistencies, e.g., jitter, drift, and identity switches.…
Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models
Yibo Wang, Jisheng Dang, Bimei Wang +7
Omni-modal large language models integrate text, audio, and image signals into a shared residual stream, where concepts such as emotion can be linearly decoded and causally modifie…
AffectOmni: RL-Verifiable People-Centric Grounded Affective Reasoning for Social and Art-Related Scenes
Yibo Wang, Rui Yang, Jisheng Dang +7
Multimodal large language models (MLLMs) achieve strong performance on VQA and scene understanding, yet affective reasoning remains vulnerable to shortcut behavior. Models may pred…
Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM Agents
Yitao Wu, Si Shen, Rui Yang +2
Verify-repair loops are a standard means for large language model (LLM) agents to correct faulty plans in code generation, mathematical reasoning, and tool use. When both the verif…
CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs
Chengwen Liu, Hao Peng, Jisheng Dang +3
In multimodal video reasoning, reinforcement learning-based methods typically rely on simplistic and inflexible reasoning-length control strategies that fail to adapt to the model'…
MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning
Shang Ma, Jisheng Dang, Wencan Zhang +6
We propose a multi-agent collaborative framework built upon a lightweight Multimodal Large Language Model (MLLM), specifically designed for social intelligence reasoning. A key fea…
On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR
Hao Ye, Jisheng Dang, Junfeng Fang +7
Recent extensive research has demonstrated that the enhanced reasoning capabilities acquired by models through Reinforcement Learning with Verifiable Rewards (RLVR) are primarily c…
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
Chengwen Liu, Xiaomin Yu, Zhuoyue Chang +15
In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore ne…