Aamer Mihaysi

O96a's activity

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

commented a paper about 5 hours ago

Negative Self-Distillation: Learning to Reason by Avoiding Flaws

Paper • 2609.11699 • Published 4 days ago • 29 •

3

commented a paper 1 day ago

Adaptive Bridge: A Proxy-Based Decoupling Layer for Mitigating DDS Backpressure in ROS 2

Paper • 2608.15380 • Published 8 days ago • 23 •

3

commented a paper 2 days ago

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

Paper • 2609.10016 • Published 5 days ago • 31 •

4

updated a model 2 days ago

O96a/sudanizer-72k

Updated 2 days ago

commented a paper 3 days ago

SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents

Paper • 2609.08149 • Published 6 days ago • 24 •

4

commented a paper 4 days ago

Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model

Paper • 2609.06008 • Published 9 days ago • 20 •

4

commented a paper 5 days ago

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Paper • 2609.04010 • Published 11 days ago • 147 •

13

commented a paper 6 days ago

Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization

Paper • 2609.05258 • Published 10 days ago • 21 •

3

commented a paper 7 days ago

Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space

Paper • 2608.29188 • Published 16 days ago • 11 •

3

commented a paper 8 days ago

DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training

Paper • 2609.04094 • Published 11 days ago • 26 •

5

commented a paper 9 days ago

Compile by Training: Turning Natural-Language Specifications into Local Neural Functions

Paper • 2609.04199 • Published 11 days ago • 383 •

4

commented a paper 10 days ago

Ignorance or Incompetence? Constructing Knowledge-Gated, Verifiable Tasks for LLM Agents

Paper • 2608.30322 • Published 14 days ago • 4 •

4

commented a paper 11 days ago

From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix

Paper • 2609.01572 • Published 13 days ago • 35 •

3

commented a paper 12 days ago

Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase

Paper • 2608.29310 • Published 16 days ago • 29 •

4

commented a paper 13 days ago

LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering

Paper • 2608.28281 • Published 17 days ago • 106 •

5

commented a paper 14 days ago

What Does an Evaluation License? A Commit-Bound Census of Claim Replay in Inspect Evals

Paper • 2608.19269 • Published 16 days ago • 6 •

3

commented a paper 15 days ago

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Paper • 2608.25518 • Published 19 days ago • 196 •

5

commented a paper 16 days ago

PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents

Paper • 2608.26530 • Published 18 days ago • 35 •

4

commented a paper 18 days ago

TorchMorph: CUDA-accelerated Morphological Transforms

Paper • 2608.24738 • Published 20 days ago • 4 •

3

commented a paper 19 days ago

Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs

Paper • 2608.20953 • Published 24 days ago • 12 •

8