Aamer Mihaysi

O96a's activity

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

commented a paper 1 day ago

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

Paper • 2609.27980 • Published 3 days ago • 4 •

3

commented a paper 2 days ago

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

Paper • 2609.25804 • Published 4 days ago • 135 •

6

commented a paper 3 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 5 days ago • 65 •

4

commented a paper 4 days ago

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

Paper • 2609.21038 • Published 9 days ago • 4 •

4

commented a paper 5 days ago

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

Paper • 2609.20715 • Published 9 days ago • 42 •

3

commented a paper 6 days ago

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

Paper • 2609.19499 • Published 10 days ago • 37 •

4

commented a paper 7 days ago

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

Paper • 2609.20511 • Published 9 days ago • 108 •

5

commented a paper 8 days ago

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

Paper • 2609.18063 • Published 10 days ago • 18 •

4

commented a paper 9 days ago

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

Paper • 2609.17320 • Published 11 days ago • 3 •

3

commented a paper 10 days ago

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

Paper • 2609.15504 • Published 12 days ago • 37 •

5

commented a paper 11 days ago

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

Paper • 2609.05824 • Published 21 days ago • 7 •

3

commented a paper 12 days ago

Negative Self-Distillation: Learning to Reason by Avoiding Flaws

Paper • 2609.11699 • Published 16 days ago • 36 •

3

commented a paper 13 days ago

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

Paper • 2608.15380 • Published 20 days ago • 26 •

4

commented a paper 14 days ago

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

Paper • 2609.10016 • Published 17 days ago • 29 •

5

updated a model 15 days ago

O96a/sudanizer-72k

Updated 15 days ago

commented a paper 15 days ago

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

Paper • 2609.08149 • Published 18 days ago • 28 •

4

commented a paper 16 days ago

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

Paper • 2609.06008 • Published 21 days ago • 19 •

4

commented a paper 17 days ago

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Paper • 2609.04010 • Published 23 days ago • 113 •

13

commented a paper 18 days ago

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

Paper • 2609.05258 • Published 22 days ago • 20 •

3

commented a paper 19 days ago

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

Paper • 2608.29188 • Published 28 days ago • 11 •

3