FW
Furu Wei
cs.CLcs.LGcs.AIcs.CVeess.AScs.IRcs.SDcs.GLcs.MAcs.MM
On Valency
published · living versionsW_ja8bdcpk·v1 · currentpublished
Catalyzing Interactive HTML Generation Capabilities via High-Fidelity Reinforcement Learning
with Xujia Wang, Yixuan Liu, Shaohan Huang, Lei Hou +2
1 version
Preprints & journals
307 papers in the corpus · 2010–2026BitNet v2: Low-Bit and Sparsified Activations for 1-Bit Large Language Models.42525934 · Wang, Hongyu, Ma, Shuming, Wei, Furu2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(11):14530-14541
OPDArena: Understanding Learning and Forgetting in On-Policy Distillation2610.25651v1 · Yuanze Xu, Tianzhu Ye, Hui Sun et al.2026 · 0 citationsarXivon Valency
Agensh: Scaling Organizational Intelligence to 1,024 Agents2609.26781v1 · Zhihao Zhan, Ting Song, Li Dong et al.2026 · 0 citationsarXiv
Learning to Coach for Experiential Learning2609.15851v1 · Guanheng Chen, Tianzhu Ye, Li Dong et al.2026 · 0 citationsarXiv
AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection2609.05899v1 · Peng Lai, He Zhu, Zhiwen Ruan et al.2026 · 0 citationsarXiv
VibeVoice-ASR-Streaming Technical Report2609.02812v2 · Yujie Tu, Zhiliang Peng, Jianwei Yu et al.2026 · 0 citationsarXiv
Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry2608.30457v1 · Jiani Guo, Junjie Wang, Jie Wu et al.2026 · 0 citationsarXiv
VibeVoice-ASR-BitNet Technical Report2607.21075v2 · Songchen Xu, Ting Song, Shaohan Huang et al.2026 · 0 citationsarXiv
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks2607.18110v1 · Tianzhu Ye, Li Dong, Guanheng Chen et al.2026 · 0 citationsarXiv
Multi-Turn On-Policy Distillation with Prefix Replay2607.04763v3 · Baohao Liao, Hanze Dong, Christof Monz et al.2026 · 0 citationsarXiv
BitNet Text Embeddings2606.25674v2 · Zhen Li, Xin Huang, Liang Wang et al.2026 · 0 citationsarXiv
Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning2606.22995v2 · Yunan Wang, Minghui Song, Zihan Zhang et al.2026 · 0 citationsarXiv
Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?2606.10956v1 · Tengchao Lv, Dongdong Zhang, Jiayu Ding et al.2026 · 0 citationsarXiv
You Only Index Once: Cross-Layer Sparse Attention with Shared Routing2606.06467v1 · Yutao Sun, Yanqi Zhang, Li Dong et al.2026 · 0 citationsarXiv
Audio-Visual Intelligence in Large Foundation Models2605.04045v1 · You Qin, Kai Liu, Shengqiong Wu et al.2026 · 0 citationsarXiv
On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length2605.02572v1 · Sunghwan Kim, Junhee Cho, Beong-woo Kwak et al.2026 · 0 citationsarXiv
Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality2605.01749v1 · Wen Luo, Guangyue Peng, Liang Wang et al.2026 · 0 citationsarXiv
RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning2604.00790v2 · Shaopeng Fu, Xingxing Zhang, Li Dong et al.2026 · 0 citationsarXiv
Universal YOCO for Efficient Depth Scaling2604.01220v1 · Yutao Sun, Li Dong, Tianzhu Ye et al.2026 · 0 citationsarXiv
Online Experiential Learning for Language Models2603.16856v2 · Tianzhu Ye, Li Dong, Qingxiu Dong et al.2026 · 0 citationsarXiv
Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models2603.07777v1 · Zongqian Li, Shaohan Huang, Zewen Chi et al.2026 · 0 citationsarXiv
Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems2603.07779v1 · Zongqian Li, Tengchao Lv, Shaohan Huang et al.2026 · 0 citationsarXiv
Learning to Draft: Adaptive Speculative Decoding with Reinforcement Learning2603.01639v1 · Jiebin Zhang, Zhenghan Yu, Liang Wang et al.2026 · 0 citationsarXiv
Synergizing Understanding and Generation with Interleaved Analyzing-Drafting Thinking2602.21435v2 · Shengqiong Wu, Bobo Li, Xinkai Wang et al.2026 · 0 citationsarXiv
On-Policy Context Distillation for Language Models2602.12275v2 · Tianzhu Ye, Li Dong, Xun Wu et al.2026 · 0 citationsarXiv
From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics2601.23048v3 · Bowen Cao, Dongdong Zhang, Yixia Li et al.2026 · 0 citationsarXiv
VIBEVOICE-ASR Technical Report2601.18184v2 · Zhiliang Peng, Jianwei Yu, Yaoyao Chang et al.2026 · 0 citationsarXiv
Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge2601.08808v1 · Yao Tang, Li Dong, Yaru Hao et al.2026 · 0 citationsarXiv
Black-Box On-Policy Distillation of Large Language Models2511.10643v3 · Tianzhu Ye, Li Dong, Zewen Chi et al.2025 · 0 citationsarXiv
QueST: Incentivizing LLMs to Generate Difficult Problems2510.17715v1 · Hanxu Hu, Xingxing Zhang, Jannis Vamvas et al.2025 · 0 citationsarXiv
Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs2509.00084v2 · Qibin Wang, Pu Zhao, Shaohan Huang et al.2025 · 0 citationsarXiv
Reasoning with Exploration: An Entropy Perspective2506.14758v4 · Daixuan Cheng, Shaohan Huang, Xuekai Zhu et al.2025 · 6 citationsarXiv
Reinforcement Pre-Training2506.08007v1 · Qingxiu Dong, Li Dong, Yao Tang et al.2025 · 0 citationsarXiv
Rectified Sparse Attention2506.04108v2 · Yutao Sun, Tianzhu Ye, Li Dong et al.2025 · 0 citationsarXiv
Think Only When You Need with Large Hybrid-Reasoning Models2505.14631v2 · Lingjie Jiang, Xun Wu, Shaohan Huang et al.2025 · 1 citationarXiv
Shorten After You're Right: Lazy Length Penalties for Reasoning RL2505.12284v3 · Danlong Yuan, Tian Xie, Shaohan Huang et al.2025 · 0 citationsarXiv
BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs2504.18415v2 · Hongyu Wang, Shuming Ma, Furu Wei2025 · 1 citationarXiv
Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes2504.15037v2 · Huanyu Zhang, Chengzu Li, Wenshan Wu et al.2025 · 0 citationsarXiv
BitNet b1.58 2B4T Technical Report2504.12285v2 · Shuming Ma, Hongyu Wang, Shaohan Huang et al.2025 · 1 citationarXiv
Model as a Game: On Numerical and Spatial Consistency for Generative Games2503.21172v1 · Jingye Chen, Yuzhong Zhao, Yupan Huang et al.2025 · 0 citationsarXiv
Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning2502.18080v2 · Wenkai Yang, Shuming Ma, Yankai Lin et al.2025 · 2 citationsarXiv
WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale2502.16684v1 · Jiaxi Li, Xingxing Zhang, Xun Wang et al.2025 · 0 citationsarXiv
Bitnet.cpp: Efficient Edge Inference for Ternary LLMs2502.11880v1 · Jinheng Wang, Hansong Zhou, Ting Song et al.2025 · 12 citationsarXiv
mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data2502.08468v1 · Haonan Chen, Liang Wang, Nan Yang et al.2025 · 6 citationsarXiv
Next Block Prediction: Video Generation via Semi-Autoregressive Modeling2502.07737v2 · Shuhuai Ren, Shuming Ma, Xu Sun et al.2025 · 0 citationsarXiv
Examining False Positives under Inference Scaling for Mathematical Reasoning2502.06217v2 · Yu Wang, Nan Yang, Liang Wang et al.2025 · 2 citationsarXiv
Chain-of-Retrieval Augmented Generation2501.14342v3 · Liang Wang, Haonan Chen, Nan Yang et al.2025 · 9 citationsarXiv
Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective2501.11110v4 · Yiyao Yu, Yuxiang Zhang, Dongdong Zhang et al.2025 · 5 citationsarXiv
Imagine while Reasoning in Space: Multimodal Visualization-of-Thought2501.07542v1 · Chengzu Li, Wenshan Wu, Huanyu Zhang et al.2025 · 0 citationsarXiv
PEACE: Empowering Geologic Map Holistic Understanding with MLLMs2501.06184v1 · Yangyu Huang, Tianyi Gao, Haoran Xu et al.2025 · 11 citationsarXiv
Career total: 447 works. 307 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.