Long(Tony) Lian PRO

longlian's activity

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

upvoted a paper 1 day ago

Reconstruction Alignment Improves Unified Multimodal Models

Paper • 2509.07295 • Published 3 days ago • 35

upvoted 3 papers 3 months ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2 • 180

REOrdering Patches Improves Vision Models

Paper • 2505.23751 • Published May 29 • 16

Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO

Paper • 2505.22453 • Published May 28 • 46

upvoted a paper 4 months ago

Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving

Paper • 2505.04528 • Published May 7 • 12

upvoted 7 papers 5 months ago

TTRL: Test-Time Reinforcement Learning

Paper • 2504.16084 • Published Apr 22 • 120

Learning Adaptive Parallel Reasoning with Language Models

Paper • 2504.15466 • Published Apr 21 • 43

Describe Anything: Detailed Localized Image and Video Captioning

Paper • 2504.16072 • Published Apr 22 • 63

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

Paper • 2504.13169 • Published Apr 17 • 39

Teaching Large Language Models to Reason with Reinforcement Learning

Paper • 2403.04642 • Published Mar 7, 2024 • 51

Token-Efficient Long Video Understanding for Multimodal LLMs

Paper • 2503.04130 • Published Mar 6 • 95

Self-Steering Language Models

Paper • 2504.07081 • Published Apr 9 • 18

upvoted 2 papers 6 months ago

TULIP: Towards Unified Language-Image Pretraining

Paper • 2503.15485 • Published Mar 19 • 49

Atlas: Multi-Scale Attention Improves Long Context Image Modeling

Paper • 2503.12355 • Published Mar 16 • 12

upvoted 2 papers 7 months ago

Towards an AI co-scientist

Paper • 2502.18864 • Published Feb 26 • 52

TransMLA: Multi-head Latent Attention Is All You Need

Paper • 2502.07864 • Published Feb 11 • 57

upvoted 3 papers 8 months ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 418

TransPixar: Advancing Text-to-Video Generation with Transparency

Paper • 2501.03006 • Published Jan 6 • 27

Training Software Engineering Agents and Verifiers with SWE-Gym

Paper • 2412.21139 • Published Dec 30, 2024 • 24

upvoted a paper 9 months ago

Deliberation in Latent Space via Differentiable Cache Augmentation

Paper • 2412.17747 • Published Dec 23, 2024 • 33