28 citations · 92 across the 52 of their papers we have counts for
55 papers
Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning
Quan M. Tran, Zhuo Huang, Zhen Fang +3
Autonomous agents increasingly rely on memory to generalize beyond their training environments. However, agents are bounded by what they have seen and believed, and leveraging such…
Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement
Xutao Mao, Jianing Zhu, Jinman Zhao +4
Reinforcement learning (RL) has substantially improved the reasoning capabilities of vision-language models (VLMs), yet it can induce chain-of-thought (CoT) obfuscation, an operati…
Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment
Suqin Yuan, Runqi Lin, Muyang Li +5
Human-feedback alignment has made language models useful assistants and is commonly described as aligning them with humans. However, the responses people prefer from an AI need not…
Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection
Jun Nie, Yonggang Zhang, Tongliang Liu +3
Robust detection of generated images is critical to counter the misuse of generative models. Existing methods primarily depend on learning from human-annotated training datasets, l…
MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs
He Li, Haoang Chi, Qizhou Wang +6
Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific co…
AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
Jingwei Sun, Jianing Zhu, Yuanyi Li +3
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-w…
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
Jingwei Sun, Jianing Zhu, Jiangchao Yao +2
To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over accumulated dialogue history. M…
Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance
Muyang Li, Yucheng Liu, Jianbo Ma +3
Vision-Language Models (VLMs) have enhanced traditional LLMs with visual capabilities through the integration of vision encoders. While recent works have explored various combinati…
Rethinking Deep Research from the Perspective of Web Content Distribution Matching
Zixuan Yu, Zhenheng Tang, Tongliang Liu +3
Despite the integration of search tools, Deep Search Agents often suffer from a misalignment between reasoning-driven queries and the underlying web indexing structures. Existing f…
i-PhysGaussian: Implicit Physical Simulation for 3D Gaussian Splatting
Yicheng Cao, Zhuo Huang, Yu Yao +3
Physical simulation predicts future states of objects based on material properties and external loads, enabling blueprints for both Industry and Engineering to conduct risk managem…
MeGU: Machine-Guided Unlearning with Target Feature Disentanglement
Haoyu Wang, Zhuo Huang, Xiaolong Wang +3
The growing concern over training data privacy has elevated the "Right to be Forgotten" into a critical requirement, thereby raising the demand for effective Machine Unlearning. Ho…
BrokenBind: Universal Modality Exploration beyond Dataset Boundaries
Zhuo Huang, Runnan Chen, Bo Han +3
Multi-modal learning combines various modalities to provide a comprehensive understanding of real-world problems. A common strategy is to directly bind different modalities togethe…
Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning
Zhuo Huang, Qizhou Wang, Ziming Hong +3
For ethical and safe AI, machine unlearning rises as a critical topic aiming to protect sensitive, private, and copyrighted knowledge from misuse. To achieve this goal, it is commo…
Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents
Quan M. Tran, Zhuo Huang, Wenbin Zhang +4
Autonomous agents excel in self-improvement through reflection and iterative refinement, which reuse successful task trajectories as in-context examples to assist subsequent reason…
Revealing Multimodal Causality with Large Language Models
Jin Li, Shoujin Wang, Qi Zhang +5
Uncovering cause-and-effect mechanisms from data is fundamental to scientific progress. While large language models (LLMs) show promise for enhancing causal discovery (CD) from uns…
Generative Model Inversion Through the Lens of the Manifold Hypothesis
Xiong Peng, Bo Han, Fengfei Yu +3
Model inversion attacks (MIAs) aim to reconstruct class-representative samples from trained models. Recent generative MIAs utilize generative adversarial networks to learn image pr…
Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning
Ali Taheri, Alireza Taban, Qizhou Wang +4
Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs), notably enhancing their capacity to acquire domain-specific knowledge while preservi…
When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
Ziming Hong, Runnan Chen, Zengmao Wang +3
Data-free knowledge distillation (DFKD) transfers knowledge from a teacher to a student without access the real in-distribution (ID) data. Its common solution is to use a generator…
Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
Haoang Chi, He Li, Wenjing Yang +5
Causal reasoning capability is critical in advancing large language models (LLMs) toward strong artificial intelligence. While versatile LLMs appear to have demonstrated capabiliti…
From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium
Xie Yi, Zhanke Zhou, Chentao Cao +3
Multi-agent frameworks can substantially boost the reasoning power of large language models (LLMs), but they typically incur heavy computational costs and lack convergence guarante…
Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
Puning Yang, Qizhou Wang, Zhuo Huang +3
Loss reweighting has shown significant benefits for machine unlearning with large language models (LLMs). However, their exact functionalities are left unclear and the optimal stra…
On the Thinking-Language Modeling Gap in Large Language Models
Chenxi Liu, Yongqiang Chen, Tongliang Liu +3
System 2 reasoning is one of the defining characteristics of intelligence, which requires slow and logical thinking. Human conducts System 2 reasoning via the language of thoughts…
Instance-dependent Early Stopping
Suqin Yuan, Runqi Lin, Lei Feng +2
In machine learning practice, early stopping has been widely used to regularize models and can save computational costs by halting the training process when the model's performance…
Noisy Test-Time Adaptation in Vision-Language Models
Chentao Cao, Zhun Zhong, Zhanke Zhou +4
Test-time adaptation (TTA) aims to address distribution shifts between source and target data by relying solely on target data during testing. In open-world scenarios, models often…