4 citations · 5 across the 12 of their papers we have counts for
13 papers
LEGO-Anything: Coding Agents for 3D Scene Reconstruction
Xirui Li, Peng Shi, Mingwen Dong +7
A 3D scene reconstructed from a single image is most useful when represented not as a rendering or a fixed 3D output, but as an explicit scene program whose execution yields a scen…
How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review
Ming Li, Chenguang Wang, Xirui Li +5
As large language models increasingly participate in scientific evaluation, we investigate a potential form of reward hacking: how rhetorical choices shape AI-review judgments when…
FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
Xirui Li, Zhe Liu, Xiaoqing Ye +4
Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action voca…
Guava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness
Haowen Liu, Xirui Li, Shaoxiong Yao +5
Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through embodied tools use offers a promising…
Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents
Xirui Li, Ming Li, Yunze Xiao +4
Collective intelligence refers to the ability of a group to achieve outcomes beyond what any individual member can accomplish alone. As large language model agents scale to populat…
ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
Xirui Li, Ming Li, Ion Stoica +2
Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dat…
When AI Navigates the Fog of War
Ming Li, Xirui Li, Tianyi Zhou
Can AI reason about a war before its trajectory becomes historically obvious? Analyzing this capability is difficult because retrospective geopolitical prediction is heavily confou…
Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
Ming Li, Xirui Li, Tianyi Zhou
As large language model agents increasingly populate networked environments, a fundamental question arises: do artificial intelligence (AI) agent societies undergo convergence dyna…
What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis
Xirui Li, Ming Li, Tianyi Zhou
Reinforcement learning (RL) with verifiable rewards has become a standard post-training stage for boosting visual reasoning in vision-language models, yet it remains unclear what c…
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Tencent Hunyuan Team, Ao Liu, Botong Zhou +248
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mam…
R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model
Hengguang Zhou, Xirui Li, Ruochen Wang +3
Recently DeepSeek R1 demonstrated how reinforcement learning with simple rule-based incentives can enable autonomous development of complex reasoning in large language models, char…
MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?
Xirui Li, Hengguang Zhou, Ruochen Wang +3
Humans are prone to cognitive distortions -- biased thinking patterns that lead to exaggerated responses to specific stimuli, albeit in very different contexts. This paper demonstr…
DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
Xirui Li, Ruochen Wang, Minhao Cheng +2
The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. Howev…