TimLeung

skytliang's activity

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

authored 17 papers 3 days ago

Exploring Human-Like Translation Strategy with Large Language Models

Paper • 2305.04118 • Published May 6, 2023

Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models

Paper • 2310.20499 • Published Oct 31, 2023 • 8

Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate

Paper • 2305.19118 • Published May 30, 2023

CriticBench: Benchmarking LLMs for Critique-Correct Reasoning

Paper • 2402.14809 • Published Feb 22, 2024 • 3

How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments

Paper • 2403.11807 • Published Mar 18, 2024

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training

Paper • 2407.09121 • Published Jul 12, 2024 • 6

Draft Model Knows When to Stop: A Self-Verification Length Policy for Speculative Decoding

Paper • 2411.18462 • Published Nov 27, 2024 • 6

Critical Tokens Matter: Token-Level Contrastive Estimation Enhence LLM's Reasoning Capability

Paper • 2411.19943 • Published Nov 29, 2024 • 62

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Paper • 2412.21187 • Published Dec 30, 2024 • 40

Teaching LLMs to Refine with Tools

Paper • 2412.16871 • Published Dec 22, 2024

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Paper • 2501.18585 • Published Jan 30, 2025 • 61

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Paper • 2504.11456 • Published Apr 15, 2025 • 12

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

Paper • 2505.14681 • Published May 20, 2025 • 10

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning

Paper • 2505.23754 • Published May 29, 2025 • 15

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

Paper • 2505.13445 • Published May 19, 2025

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

Paper • 2503.02875 • Published Mar 4, 2025 • 1

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

Paper • 2512.19673 • Published Dec 22, 2025 • 64