Noah

noahml's activity

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

commented a paper about 3 hours ago

KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

Paper • 2606.03458 • Published 3 days ago • 46 •

8

commented a paper about 4 hours ago

KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

Paper • 2606.03458 • Published 3 days ago • 46 •

8

commented 3 papers about 5 hours ago

KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

Paper • 2606.03458 • Published 3 days ago • 46 •

8

OCC-RAG: Optimal Cognitive Core for Faithful Question Answering

Paper • 2606.00683 • Published 6 days ago • 81 •

6

Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching

Paper • 2606.03911 • Published 3 days ago • 19 •

2

commented a paper 1 day ago

Policy and World Modeling Co-Training for Language Agents

Paper • 2606.02388 • Published 4 days ago • 11 •

3

commented 7 papers 2 days ago

Trust-Region Behavior Blending for On-Policy Distillation

Paper • 2605.31159 • Published 7 days ago • 64 •

4

Mellum2 Technical Report

Paper • 2605.31268 • Published 7 days ago • 51 •

3

A Formally Verified Library of Mathematical Finance in Lean 4

Paper • 2606.01356 • Published 5 days ago • 1 •

3

MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation

Paper • 2606.02470 • Published 4 days ago • 16 •

3

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

Paper • 2606.02031 • Published 4 days ago • 16 •

3

PEEK: Picking Essential frames via Efficient Knowledge distillation

Paper • 2605.31029 • Published 7 days ago • 19 •

7

PEEK: Picking Essential frames via Efficient Knowledge distillation

Paper • 2605.31029 • Published 7 days ago • 19 •

7

commented 2 papers 3 days ago

Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation

Paper • 2605.22765 • Published 15 days ago • 4 •

3

PEEK: Picking Essential frames via Efficient Knowledge distillation

Paper • 2605.31029 • Published 7 days ago • 19 •

7

commented 5 papers 4 days ago

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

Paper • 2605.30161 • Published 8 days ago • 59 •

3

When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems

Paper • 2605.30102 • Published 8 days ago • 15 •

3

REPOT: Recoverable Program-of-Thought via Checkpoint Repair

Paper • 2605.30052 • Published 8 days ago • 10 •

3

Thinking Before Constraining: A Unified Decoding Framework for Large Language Models

Paper • 2601.07525 • Published 8 days ago • 10 •

3

Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases

Paper • 2605.27355 • Published 10 days ago • 7 •

3