15 papers
ClashBench: Conflicts Leading Agents to Seize and Harm
Yuejin Xie, Yu Li, Dadi Guo +6
As agent systems become more widely used, multiple agent sessions increasingly run alongside pre-existing user tasks in the same environment, sharing resources with limited capacit…
SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment
Qinghua Mao, Wanying Qu, Dadi Guo +8
The performance of LLM-based agents is jointly shaped by the base model and the harness used when interacting with the environment. This exposes them to safety risks in both harmfu…
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
Zhijie Zheng, Yu Li, Chen Qian +5
LLM-based agents can interact with external environments through tool invocation, but this capability also introduces security risks such as file modification, information leakage,…
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
Wanying Qu, Qinghua Mao, Yu Li +12
The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime contro…
What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing
Hangyu Lin, Chao Wen, Chengming Xu +4
Flow matching based video generative models have been increasingly relying on prepended Vision-Language Models (VLMs) to handle complex, instruction-based video editing. The prevai…
StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
Ming Xie, Zizheng Huang, Xudong Tan +6
While streaming omni-video understanding demands continuous perception and proactive, real-time interaction, this crucial area remains largely under-explored. Current omni-modal me…
Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance
Runze Wang, Yuqian Fu, Yu Li +7
Vision-language-action (VLA) models have shown strong potential for generalist robot manipulation, yet they remain limited by insufficient spatial reasoning, particularly in determ…
Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent
Zeyuan Wang, Da Li, Yulin Chen +6
Combining entropy regularisation with mirror descent in online off-policy reinforcement learning requires expressive policies with efficient sampling and explicit entropy control.…
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Xinlei Yu, Zhangquan Chen, Yongbo He +36
Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an inc…
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
Yu Li, Haoyu Luo, Yuejin Xie +10
Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or…
Modeling Spatiotemporal Neural Frames for High Resolution Brain Dynamic
Wanying Qu, Jianxiong Gao, Wei Wang +1
Capturing dynamic spatiotemporal neural activity is essential for understanding large-scale brain mechanisms. Functional magnetic resonance imaging (fMRI) provides high-resolution…
COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability
Yizhuo Ding, Mingkang Chen, Qiuhua Liu +7
Large Multimodal Reasoning Models (LMRMs) are moving into real applications, where they must be both useful and safe. Safety is especially challenging in multimodal settings: image…
UniPruning: Unifying Local Metric and Global Feedback for Scalable Sparse LLMs
Yizhuo Ding, Wanying Qu, Jiawei Geng +2
Large Language Models (LLMs) achieve strong performance across diverse tasks but face prohibitive computational and memory costs. Pruning offers a promising path by inducing sparsi…
VTPerception-R1: Enhancing Multimodal Reasoning via Explicit Visual and Textual Perceptual Grounding
Yizhuo Ding, Mingkang Chen, Zhibang Feng +4
Multimodal large language models (MLLMs) often struggle to ground reasoning in perceptual evidence. We present a systematic study of perception strategies-explicit, implicit, visua…
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law
Shanghai AI Lab, :, Yicheng Bao +115
We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framewo…