Peiyong Wang PRO

Addwater's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection about 7 hours ago

cwm

Collection

Collection for Code World Model, an agentic coding model from FAIR. • 3 items • Updated 12 days ago • 15

upvoted 2 papers about 7 hours ago

Self-Improvement in Multimodal Large Language Models: A Survey

Paper • 2510.02665 • Published 3 days ago • 8

Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition

Paper • 2510.01068 • Published 5 days ago • 12

upvoted 8 papers 3 days ago

ExGRPO: Learning to Reason from Experience

Paper • 2510.02245 • Published 4 days ago • 65

TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis

Paper • 2510.01538 • Published 4 days ago • 4

Optimal Control Meets Flow Matching: A Principled Route to Multi-Subject Fidelity

Paper • 2510.02315 • Published 4 days ago • 5

A Rigorous Benchmark with Multidimensional Evaluation for Deep Research Agents: From Answers to Reports

Paper • 2510.02190 • Published 4 days ago • 13

Transformers Discover Molecular Structure Without Graph Priors

Paper • 2510.02259 • Published 4 days ago • 5

Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures

Paper • 2509.25045 • Published 7 days ago • 2

It Takes Two: Your GRPO Is Secretly DPO

Paper • 2510.00977 • Published 5 days ago • 25

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

Paper • 2509.25454 • Published 7 days ago • 117

upvoted 2 papers 5 days ago

Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play

Paper • 2509.25541 • Published 6 days ago • 122

Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents

Paper • 2509.26539 • Published 6 days ago • 7

upvoted 3 papers 6 days ago

Sequential Diffusion Language Models

Paper • 2509.24007 • Published 8 days ago • 34

MathBode: Frequency-Domain Fingerprints of LLM Mathematical Reasoning

Paper • 2509.23143 • Published 9 days ago • 4

Hyperspherical Latents Improve Continuous-Token Autoregressive Generation

Paper • 2509.24335 • Published 7 days ago • 6

upvoted a paper 10 days ago

Tree Search for LLM Agent Reinforcement Learning

Paper • 2509.21240 • Published 11 days ago • 84

upvoted a paper 11 days ago

EmbeddingGemma: Powerful and Lightweight Text Representations

Paper • 2509.20354 • Published 12 days ago • 36

upvoted 2 papers 12 days ago

Soft Tokens, Hard Truths

Paper • 2509.19170 • Published 13 days ago • 15

Reinforcement Learning on Pre-Training Data

Paper • 2509.19249 • Published 13 days ago • 62