Aamer Mihaysi

O96a's activity

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

commented a paper about 4 hours ago

The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction

Paper • 2609.18063 • Published 1 day ago • 7 •

3

commented a paper 1 day ago

Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems

Paper • 2609.17320 • Published 3 days ago • 2 •

2

commented a paper 2 days ago

How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus

Paper • 2609.15504 • Published 4 days ago • 30 •

5

commented a paper 3 days ago

Beyond Top-$k$ Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents

Paper • 2609.05824 • Published 13 days ago • 6 •

3

commented a paper 4 days ago

Negative Self-Distillation: Learning to Reason by Avoiding Flaws

Paper • 2609.11699 • Published 8 days ago • 37 •

3

commented a paper 5 days ago

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

Paper • 2608.15380 • Published 12 days ago • 27 •

4

commented a paper 6 days ago

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

Paper • 2609.10016 • Published 9 days ago • 33 •

5

updated a model 6 days ago

O96a/sudanizer-72k

Updated 6 days ago

commented a paper 7 days ago

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

Paper • 2609.08149 • Published 10 days ago • 28 •

4

commented a paper 8 days ago

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

Paper • 2609.06008 • Published 13 days ago • 21 •

4

commented a paper 9 days ago

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Paper • 2609.04010 • Published 15 days ago • 152 •

13

commented a paper 10 days ago

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

Paper • 2609.05258 • Published 14 days ago • 21 •

3

commented a paper 11 days ago

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

Paper • 2608.29188 • Published 20 days ago • 11 •

3

commented a paper 12 days ago

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

Paper • 2609.04094 • Published 15 days ago • 26 •

5

commented a paper 13 days ago

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

Paper • 2609.04199 • Published 15 days ago • 385 •

4

commented a paper 14 days ago

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

Paper • 2608.30322 • Published 18 days ago • 4 •

4

commented a paper 15 days ago

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

Paper • 2609.01572 • Published 17 days ago • 36 •

3

commented a paper 16 days ago

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

Paper • 2608.29310 • Published 20 days ago • 29 •

4

commented a paper 17 days ago

LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering

Paper • 2608.28281 • Published 21 days ago • 106 •

5

commented a paper 18 days ago

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

Paper • 2608.19269 • Published 20 days ago • 6 •

3