2 citations · 8 across the 16 of their papers we have counts for
18 papers
VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness
Zihao Lin, Haoyu Dong, Haobo Xu +10
LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reasoning, and memory. Recursive h…
GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing
Zihao Lin, Haibo Wang, Zhiyang Xu +7
Music-grounded mashup video creation is a challenging form of video non-linear editing, where a system must compose a coherent timeline from large collections of source videos whil…
IR: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
Mohammad Beigi, Ming Jin, Junshan Zhang +3
Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking - models exploit spurious correlations in proxy rewards without ge…
Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking
Mohammad Beigi, Ming Jin, Junshan Zhang +2
Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned reward models to achieve high scores w…
How Do Large Language Models Learn Concepts During Continual Pre-Training?
Barry Menglong Yao, Sha Li, Yunzhi Yao +4
Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and learning. However, how large lan…
Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories
Mohammad Beigi, Ying Shen, Parshin Shojaee +5
Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster \textit{sycophancy}, i.e., the tendency of a model to agree with or re…
Pisces: An Auto-regressive Foundation Model for Image Understanding and Generation
Zhiyang Xu, Jiuhai Chen, Zhaojiang Lin +10
Recent advances in large language models (LLMs) have enabled multimodal foundation models to tackle both image understanding and generation within a unified framework. Despite thes…
AR-RAG: Autoregressive Retrieval Augmentation for Image Generation
Jingyuan Qi, Zhiyang Xu, Qifan Wang +1
We introduce Autoregressive Retrieval Augmentation (AR-RAG), a novel paradigm that enhances image generation by autoregressively incorporating knearest neighbor retrievals at the p…
Error-driven Data-efficient Large Multimodal Model Tuning
Barry Menglong Yao, Qifan Wang, Lifu Huang
Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory pe…
RoRA-VLM: Robust Retrieval-Augmented Vision Language Models
Jingyuan Qi, Zhiyang Xu, Rulin Shao +5
Current vision-language models (VLMs) still exhibit inferior performance on knowledge-intensive tasks, primarily due to the challenge of accurately encoding all the associations be…
Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
Haibo Wang, Zhiyang Xu, Yu Cheng +6
Video Large Language Models (Video-LLMs) have demonstrated remarkable capabilities in coarse-grained video understanding, however, they struggle with fine-grained temporal groundin…
Modality-Specialized Synergizers for Interleaved Vision-Language Generalists
Zhiyang Xu, Minqian Liu, Ying Shen +5
Recent advancements in Vision-Language Models (VLMs) have led to the emergence of Vision-Language Generalists (VLGs) capable of understanding and generating both text and images. H…
InternalInspector : Robust Confidence Estimation in LLMs through Internal States
Mohammad Beigi, Ying Shen, Runing Yang +7
Despite their vast capabilities, Large Language Models (LLMs) often struggle with generating reliable outputs, frequently producing high-confidence inaccuracies known as hallucinat…
Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning
Zhiyang Xu, Chao Feng, Rulin Shao +6
Despite vision-language models' (VLMs) remarkable capabilities as versatile visual assistants, two substantial challenges persist within the existing VLM frameworks: (1) lacking ta…
Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models
Zihao Lin, Mohammad Beigi, Hongxuan Li +5
Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new facts into Large Language Models (LLMs). Two mainstream ME methods exist: parameter-m…
Multimodal Instruction Tuning with Conditional Mixture of LoRA
Ying Shen, Zhiyang Xu, Qifan Wang +3
Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in diverse tasks across different domains, with an increasing focus on improving their zero-shot g…
The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models
Jingyuan Qi, Zhiyang Xu, Ying Shen +4
Chain-of-Thought (CoT) prompting enables large language models to solve complex reasoning problems by generating intermediate steps. However, confined by its inherent single-pass a…
AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributes
Barry Menglong Yao, Sijia Wang, Yu Chen +5
We propose attribute-aware multimodal entity linking, where the input consists of a mention described with a text paragraph and images, and the goal is to predict the corresponding…