6 citations · 6 across the 13 of their papers we have counts for
15 papers
Unlocking Token Rewards via Training-Free Reward Attribution
Sitong Wu, Haoru Tan, Bin Xia +6
In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward model. Our core idea is to attrib…
Dynamic Important Example Mining for Reinforcement Finetuning
Haoru Tan, Sitong Wu, Yanfeng Chen +9
Reinforcement fine-tuning (RFT) is increasingly used to strengthen the reasoning abilities of large models, yet its effectiveness is bound by how training data are selected and use…
StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding
Xichen Zhang, Guankai Li, Yinghao Zhu +6
Deploying autonomous multimodal agents in continuous, real-world environments requires them to ingest unbounded audio-visual streams and maintain hour-scale memory. However, curren…
Dataset Distillation by Influence Matching
Haoru Tan, Wang Wang, Sitong Wu +5
We revisit dataset distillation from an outcome-centric perspective. Rather than aligning process surrogates (per-step gradients or training trajectories), Influence Matching (Inf-…
FastMix: Fast Data Mixture Optimization via Gradient Descent
Haoru Tan, Sitong Wu, Yanfeng Chen +5
While large and diverse datasets have driven recent advances in large models, identifying the optimal data mixture for pre-training and post-training remains a significant open pro…
Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention
Wenhu Zhang, Yiming Wu, Huanyu Wang +6
Diffusion Language Models (DLMs) enable globally coherent, bidirectional, and controllable text generation, offering advantages over traditional autoregressive LLMs, while scaling…
SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation
Xichen Zhang, Ziyi He, Yinghao Zhu +6
Search agents have emerged as a pivotal paradigm for solving open-ended, knowledge-intensive reasoning tasks. However, training these agents via Reinforcement Learning (RL) faces a…
SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration
Xichen Zhang, Sitong Wu, Haoru Tan +4
The long chain-of-thought (LongCoT) capability is central to the recent breakthroughs achieved by large language models in complex reasoning tasks. However, the accompanying issue…
DreamOmni2: Multimodal Instruction-based Editing and Generation
Bin Xia, Bohao Peng, Yuechen Zhang +10
Recent advancements in instruction-based image editing and subject-driven generation have garnered significant attention, yet both tasks still face limitations in meeting practical…
Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
Xichen Zhang, Sitong Wu, Yinghao Zhu +4
Reinforcement learning from verifiable rewards has emerged as a powerful technique for enhancing the complex reasoning abilities of Large Language Models (LLMs). However, these met…
Understanding Data Influence with Differential Approximation
Haoru Tan, Sitong Wu, Xiuzhe Wu +5
Data plays a pivotal role in the groundbreaking advancements in artificial intelligence. The quantitative analysis of data significantly contributes to model training, enhancing bo…
Data Pruning by Information Maximization
Haoru Tan, Sitong Wu, Wei Huang +2
In this paper, we present InfoMax, a novel data pruning method, also known as coreset selection, designed to maximize the information content of selected samples while minimizing r…
Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
Zhisheng Zhong, Chengyao Wang, Yuqi Liu +12
As Multi-modal Large Language Models (MLLMs) evolve, expanding beyond single-domain capabilities is essential to meet the demands for more versatile and efficient AI. However, prev…
Ensemble Quadratic Assignment Network for Graph Matching
Haoru Tan, Chuang Wang, Sitong Wu +3
Graph matching is a commonly used technique in computer vision and pattern recognition. Recent data-driven approaches have improved the graph matching accuracy remarkably, whereas…
Data Pruning via Moving-one-Sample-out
Haoru Tan, Sitong Wu, Fei Du +4
In this paper, we propose a novel data-pruning approach called moving-one-sample-out (MoSo), which aims to identify and remove the least informative samples from the training set.…