3 citations · 3 across the 21 of their papers we have counts for
26 papers
ReasonUni: Reasoning-Augmented Reconstruction Advances Unified Multimodal Models
Feize Wu, Zhiyuan Yan, Yuhuan Hong +10
Image-to-text (I2T) understanding and text-to-image (T2I) generation are dual tasks in unified multimodal models (UMMs). Reconstructive post-training couples these tasks, but exist…
Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models
Mingyue Cui, Zheyuan Liu, Yihan Zhu +2
Vision-language-action (VLA) models generalize broadly across robotic manipulation tasks, but complex environments require balancing task success with unintended contact. Runtime s…
CheatBench: Measuring Reward Gaming in AI Agents
Long Phan, Stephen K. Yang, Jason J. Lim +10
Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recent incidents and controlled e…
ManGo: Manga Active Narrative Grounding Optimization
Hao Qiu, Junyan Wang, Zheyuan Liu +4
Manga visual question answering requires models to answer questions over panel-based visual narratives, where relevant evidence is distributed across ordered panels, embedded text,…
Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives
Zheyuan Liu, Weiliang Zhao, Xiangchi Yuan +3
Large language models are increasingly deployed as autonomous agents serving users on behalf of companies, placing them in settings where user and deployer interests can conflict.…
Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents
Baicheng Chen, Zheyuan Liu, Jingyu Zhang +4
Large language models (LLMs) are increasingly deployed as tool-augmented agents, where responses can depend on tool calls and external observations rather than model parameters alo…
UniWorld-Design: From Pixel Generation to Layer-Native Design
Zongjian Li, Zhiyuan Yan, Chenxu Bai +9
We introduce UniWorld-Design, a framework that redefines image generation from flat pixel synthesis to structured visual composition, with semantic RGBA layers as the atomic units…
MemoHarness: Agent Harnesses That Learn from Experience
Yue Huang, Wenjie Wang, Han Bao +7
An agent harness is the external control layer that turns a base LLM into an executable agent by managing context, tools, orchestration, memory, decoding, and output handling. Whil…
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
Straight-Path Flow Matching for Incomplete Multi-View Clustering
Yiteng Yuan, Junyan Wang, Zheyuan Liu +4
Incomplete Multi-View Clustering addresses the problem of clustering multi-modal data when certain views are missing. Recent end-to-end generative approaches leverage diffusion mod…
GEAR: Guided End-to-End AutoRegression for Image Synthesis
Bin Lin, Zheyuan Liu, Chenguo Lin +8
Visual generative models are typically trained in two stages. A tokenizer is first trained for reconstruction and then frozen, after which a generator is trained on its discrete in…
AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?
Zhangchen Xu, Junda Chen, Yue Huang +16
Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifac…
3DEditSafe: Defending 3D Editing Pipelines from Unsafe Generation
Nicole Meng, Zheyuan Liu, Meng Jiang +1
Recent advances in 3D generative editing, particularly pipelines based on 3D Gaussian Splatting (3DGS), have achieved high-fidelity, multi-view-consistent scene manipulation from t…
Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning
Chenlu Ding, Jiancan Wu, Yanchen Luo +3
Large language models (LLMs) often fail to reason under temporal cutoffs: when prompted to answer from the standpoint of an earlier time, they exploit knowledge that became availab…
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
Diancheng Kang, Zheyuan Liu, Ningshan Ma +3
Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful…
MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues
Zheyuan Liu, Dongwhi Kim, Yixin Wan +4
Multimodal large language models (MLLMs) are increasingly deployed as assistants that interact through text and images, making it crucial to evaluate contextual safety when risk de…
Instant Personalized Large Language Model Adaptation via Hypernetwork
Zhaoxuan Tan, Zixuan Zhang, Haoyang Wen +8
Personalized large language models (LLMs) tailor content to individual preferences using user profiles or histories. However, existing parameter-efficient fine-tuning (PEFT) method…
AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning
Mengzhao Jia, Zhihan Zhang, Ignacio Cases +3
Multimodal large language models (MLLMs) have rapidly advanced from perception tasks to complex multi-step reasoning, yet reinforcement learning with verifiable rewards (RLVR) ofte…
Dual-Space Smoothness for Robust and Balanced LLM Unlearning
Han Yan, Zheyuan Liu, Meng Jiang
As large language models evolve, Machine Unlearning has emerged to address growing concerns around user privacy, copyright infringement, and overall safety. Yet state-of-the-art (S…
Steering Multimodal Large Language Models Decoding for Context-Aware Safety
Zheyuan Liu, Zhangchen Xu, Guangyao Dou +4
Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet their ability to make context-aware safety decisions remains limited. Existing me…
Incorporating Rather Than Eliminating: Achieving Fairness for Skin Disease Diagnosis Through Group-Specific Expert
Gelei Xu, Yuying Duan, Zheyuan Liu +5
AI-based systems have achieved high accuracy in skin disease diagnostics but often exhibit biases across demographic groups, leading to inequitable healthcare outcomes and diminish…
Graph Foundation Models: A Comprehensive Survey
Zehong Wang, Zheyuan Liu, Tianyi Ma +16
Graph-structured data pervades domains such as social networks, biological systems, knowledge graphs, and recommender systems. While foundation models have transformed natural lang…
Superficial Self-Improved Reasoners Benefit from Model Merging
Xiangchi Yuan, Chunhui Zhang, Zheyuan Liu +4
As scaled language models (LMs) approach human-level reasoning capabilities, self-improvement emerges as a solution to synthesizing high-quality data corpus. While previous researc…
Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey
Bo Ni, Zheyuan Liu, Leyao Wang +17
Retrieval-Augmented Generation (RAG) is an advanced technique designed to address the challenges of Artificial Intelligence-Generated Content (AIGC). By integrating context retriev…