1 citations · 1 across the 21 of their papers we have counts for
22 papers
MemWM: Memory-Augmented Text-Based World Model
Yujun Wang, Tao Zhang, Jinhe Bi +9
World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can sti…
MAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy
Aniri, Chen Yilin, Jinhe Bi +10
Vision-Language-Action models (VLAs) integrate visual perception, language instruction, and action generation into end-to-end policies across heterogeneous architectures. However,…
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
Aniri, Jinhe Bi, Peng Liao +5
On-Policy Self-Distillation (OPSD) has become a standard post-training approach for improving visual reasoning in multimodal large language models (MLLMs). Existing methods draw pr…
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Jinhe Bi, Chennan Zhou, Zengjie Jin +10
On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories…
MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
Zefeng Wang, Minxi Yan, Jinhe Bi +3
Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability. Howe…
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence
Xuanle Zhao, Qiushi Sun, Jingyu Xiao +16
While Large Language Models (LLMs) have substantially advanced text-to-code generation, many real programming tasks specify intent through visual artifacts such as screenshots, cha…
EchoRL: Reinforcement Learning via Rollout Echoing
Jinhe Bi, Aniri, Minglai Yang +9
Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceed…
PyraVid: Hierarchical Multimodal Memory for Long-Horizon Video Reasoning
Sikuan Yan, Sicheng Dong, Haotong Wang +8
Memory has become an increasingly important component of agentic systems, as these systems are expected to reason over long-term experience. However, prior work has largely focused…
Graph is a Substrate Across Data Modalities
Ziming Li, Xiaoming Wu, Zehong Wang +6
Graphs provide a natural representation of relational structure that arises across diverse domains. Despite this ubiquity, graph structure is typically learned in a modality- and t…
AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models
Haokun Chen, Jianing Li, Yao Zhang +4
Multimodal Large Language Models (MLLMs) achieve impressive performance once optimized on massive datasets. Such datasets often contain sensitive or copyrighted content, raising si…
Reinforcement Mid-Training
Yijun Tian, Shaoyu Chen, Zhichao Xu +4
The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an addit…
MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media
Rui Lu, Jinhe Bi, Yunpu Ma +3
Social media has evolved into a complex multimodal environment where text, images, and other signals interact to shape nuanced meanings, often concealing harmful intent. Identifyin…
Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
Guancheng Wan, Lucheng Fu, Haoxin Liu +10
The performance of Large Language Models (LLMs) hinges on carefully engineered prompts. However, prevailing prompt optimization methods, ranging from heuristic edits and reinforcem…
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
Xingyue Huang, Rishabh, Gregor Franke +43
Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RL…
ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
Yujun Wang, Aniri, Jinhe Bi +2
Multimodal large language models (MLLMs) frequently hallucinate by over-committing to spurious visual cues. Prior remedies-Visual and Instruction Contrastive Decoding (VCD, ICD)-mi…
Backdoor Cleaning without External Guidance in MLLM Fine-tuning
Xuankun Rong, Wenke Huang, Jian Liang +5
Multimodal Large Language Models (MLLMs) are increasingly deployed in fine-tuning-as-a-service (FTaaS) settings, where user-submitted datasets adapt general-purpose models to downs…
CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process
Jinhe Bi, Danqi Yan, Yifan Wang +8
Recent Large Reasoning Models significantly improve the reasoning ability of Large Language Models by learning to reason, exhibiting the promising performance in solving complex ta…
Does Machine Unlearning Truly Remove Knowledge?
Haokun Chen, Yueqi Zhang, Yuan Bi +9
In recent years, Large Language Models (LLMs) have achieved remarkable advancements, drawing significant attention from the research community. Their capabilities are largely attri…
PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
Jinhe Bi, Aniri, Zengjie Jin +11
Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications. However, the rapid growth of these d…
LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
Jinhe Bi, Yujun Wang, Haokun Chen +4
Multimodal Large Language Models (MLLMs) have significantly advanced visual tasks by integrating visual representations into large language models (LLMs). The textual modality, inh…
FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models
Haokun Chen, Hang Li, Yao Zhang +7
One-Shot Federated Learning (OSFL), a special decentralized machine learning paradigm, has recently gained significant attention. OSFL requires only a single round of client data o…
SPOT! Revisiting Video-Language Models for Event Understanding
Gengyuan Zhang, Jinhe Bi, Jindong Gu +2
Understanding videos is an important research topic for multimodal learning. Leveraging large-scale datasets of web-crawled video-text pairs as weak supervision has become a pre-tr…