YangWang92

yangwang92's activity

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

upvoted a paper 16 days ago

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

Paper • 2511.08577 • Published 25 days ago • 104

upvoted a paper 19 days ago

Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence

Paper • 2511.07384 • Published 26 days ago • 16

upvoted a collection 19 days ago

Retrofitting Recurrence

Collection

40 items • Updated 25 days ago • 6

upvoted a paper 25 days ago

DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation

Paper • 2511.06307 • Published 27 days ago • 50

upvoted a collection about 1 month ago

LLaDA 2.0

Collection

4 items • Updated 10 days ago • 20

upvoted 4 papers about 2 months ago

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Paper • 2505.06708 • Published May 10 • 6

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paper • 2510.11696 • Published Oct 13 • 176

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published Oct 13 • 165

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs

Paper • 2507.07996 • Published Jul 10 • 34

upvoted a collection about 2 months ago

L1

Collection

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning • 7 items • Updated Jul 13 • 8

upvoted a paper about 2 months ago

TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments

Paper • 2510.01179 • Published Oct 1 • 25

upvoted a paper 2 months ago

Soft Tokens, Hard Truths

Paper • 2509.19170 • Published Sep 23 • 15

upvoted a collection 3 months ago

Qwen3-Next

Collection

4 items • Updated Sep 22 • 161

upvoted 2 papers 3 months ago

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

Paper • 2508.14444 • Published Aug 20 • 38

TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

Paper • 2508.17445 • Published Aug 24 • 80

upvoted a collection 3 months ago

NVIDIA Nemotron V2

Collection

Open, Production-ready Enterprise Models. Nvidia Open Model license. • 9 items • Updated 2 days ago • 91

upvoted a paper 4 months ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7 • 151

upvoted 3 collections 4 months ago

Recurrent Models

Collection

These are checkpoints for recurrent LLMs developed to scale test-time compute by recurring in latent space. • 15 items • Updated May 21 • 11

Web-SSL

Collection

17 items • Updated Apr 23 • 20

Physics of Language Models: Part 4.2

Collection

16 items • Updated Jul 29 • 8