Aamer Mihaysi

O96a's activity

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

commented a paper about 14 hours ago

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

Paper • 2608.26530 • Published 2 days ago • 25 •

3

commented a paper 3 days ago

TorchMorph: CUDA-accelerated Morphological Transforms

Paper • 2608.24738 • Published 4 days ago • 3 •

3

commented a paper 4 days ago

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

Paper • 2608.20953 • Published 8 days ago • 10 •

4

commented a paper 5 days ago

Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference

Paper • 2608.20210 • Published 9 days ago • 8 •

4

commented a paper 6 days ago

QuoteBench: How Matched Scores Can Hide Command-Path Failures

Paper • 2608.13547 • Published 16 days ago • 8 •

4

commented a paper 7 days ago

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

Paper • 2608.12875 • Published 16 days ago • 15 •

5

commented a paper 8 days ago

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

Paper • 2608.19799 • Published 9 days ago • 64 •

4

commented a paper 9 days ago

SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents

Paper • 2608.18852 • Published 10 days ago • 7 •

3

commented a paper 11 days ago

How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks

Paper • 2608.14905 • Published 15 days ago • 30 •

4

commented a paper 12 days ago

Second Thought: Reasoning in Parallel as LLM Agents Act and Observe

Paper • 2608.13667 • Published 15 days ago • 16 •

4

commented a paper 15 days ago

Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review

Paper • 2608.12440 • Published 17 days ago • 10 •

5

commented a paper 16 days ago

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control

Paper • 2608.12123 • Published 17 days ago • 2 •

3

commented 3 papers 17 days ago

Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents

Paper • 2608.08389 • Published 20 days ago • 12 •

3

Business Arena: Benchmarking LLM Agents in a Realistic Marketplace

Paper • 2608.08621 • Published 20 days ago • 22 •

5

Omega-S: A Functional Resilience Index for LLM Fine-Tuning

Paper • 2608.03887 • Published 25 days ago • 7 •

5

commented 2 papers 18 days ago

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published 19 days ago • 116 •

3

Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression

Paper • 2608.04569 • Published 24 days ago • 14 •

3

commented a paper 19 days ago

Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss

Paper • 2608.03796 • Published 25 days ago • 17 •

4

liked a model 19 days ago

HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

Image-Text-to-Text • 35B • Updated Apr 17 • 2.3M • 3.54k

commented a paper 20 days ago

DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces

Paper • 2608.03451 • Published 25 days ago • 33 •

4