Aamer Mihaysi

O96a's activity

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

commented a paper about 15 hours ago

Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

Paper • 2610.11794 • Published 2 days ago • 27 •

4

commented a paper 1 day ago

A self-learning scientific agent for X-ray diffraction

Paper • 2610.07862 • Published 4 days ago • 16 •

6

commented a paper 3 days ago

Source Identification Is Not Fitness Testing: Measuring the Limits of Synthetic-Data Attribution

Paper • 2610.00417 • Published 10 days ago • 2 •

4

commented a paper 4 days ago

UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents

Paper • 2610.05622 • Published 6 days ago • 21 •

3

commented a paper 5 days ago

VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks

Paper • 2610.00972 • Published 9 days ago • 59 •

3

commented a paper 9 days ago

Safety of Latent Communication in Multi-Agent Systems

Paper • 2609.39788 • Published 10 days ago • 9 •

2

commented a paper 10 days ago

SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents

Paper • 2609.34518 • Published 12 days ago • 4 •

3

commented a paper 11 days ago

Nereus: Adaptive Parallelism for LLM Post-Training

Paper • 2609.34645 • Published 12 days ago • 20 •

3

commented a paper 16 days ago

Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery

Paper • 2609.27980 • Published 17 days ago • 6 •

3

commented a paper 17 days ago

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

Paper • 2609.25804 • Published 18 days ago • 164 •

6

commented a paper 18 days ago

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

Paper • 2609.24220 • Published 19 days ago • 68 •

4

commented a paper 19 days ago

Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy

Paper • 2609.21038 • Published 23 days ago • 5 •

4

commented a paper 20 days ago

Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL

Paper • 2609.20715 • Published 23 days ago • 44 •

3

commented a paper 21 days ago

Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling

Paper • 2609.19499 • Published 24 days ago • 37 •

4

commented a paper 22 days ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published 23 days ago • 115 •

5

commented a paper 23 days ago

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

Paper • 2609.18063 • Published 24 days ago • 26 •

4

commented a paper 24 days ago

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

Paper • 2609.17320 • Published 25 days ago • 4 •

3

commented a paper 25 days ago

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

Paper • 2609.15504 • Published 26 days ago • 37 •

5

commented a paper 26 days ago

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

Paper • 2609.05824 • Published Sep 5 • 7 •

3

commented a paper 27 days ago

Negative Self-Distillation: Learning to Reason by Avoiding Flaws

Paper • 2609.11699 • Published about 1 month ago • 37 •

3