Ashwin Burnwal

AshBlanc's activity

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

upvoted 2 papers 8 days ago

Emergence of Linear Truth Encodings in Language Models

Paper • 2510.15804 • Published 18 days ago • 2

Reasoning with Sampling: Your Base Model is Smarter Than You Think

Paper • 2510.14901 • Published 19 days ago • 44

upvoted 2 papers 9 days ago

Planned Diffusion

Paper • 2510.18087 • Published 14 days ago • 6

Expanding the Action Space of LLMs to Reason Beyond Language

Paper • 2510.07581 • Published 26 days ago • 7

upvoted 8 papers about 1 month ago

LongCodeZip: Compress Long Context for Code Language Models

Paper • 2510.00446 • Published Oct 1 • 107

PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning

Paper • 2509.19894 • Published Sep 24 • 32

Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval

Paper • 2509.21710 • Published Sep 26 • 17

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published Sep 26 • 180

Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution

Paper • 2509.21072 • Published Sep 25 • 15

StyleBench: Evaluating thinking styles in Large Language Models

Paper • 2509.20868 • Published Sep 25 • 3

Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality

Paper • 2509.10402 • Published Sep 12 • 5

CodePrompt: Improving Source Code-Related Classification with Knowledge Features through Prompt Learning

Paper • 2401.05544 • Published Jan 10, 2024 • 1

upvoted 4 papers about 2 months ago

QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

Paper • 2509.09995 • Published Sep 12 • 14

Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

Paper • 2509.06917 • Published Sep 8 • 41

Reverse-Engineered Reasoning for Open-Ended Generation

Paper • 2509.06160 • Published Sep 7 • 147

ConfTuner: Training Large Language Models to Express Their Confidence Verbally

Paper • 2508.18847 • Published Aug 26 • 2

upvoted a paper 2 months ago

SSRL: Self-Search Reinforcement Learning

Paper • 2508.10874 • Published Aug 14 • 94

upvoted 3 papers 3 months ago

Puppeteer: Rig and Animate Your 3D Models

Paper • 2508.10898 • Published Aug 14 • 31

Aryabhata: An exam-focused language model for JEE Math

Paper • 2508.08665 • Published Aug 12 • 16

The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage

Paper • 2508.09603 • Published Aug 13 • 2