Aamer Mihaysi

O96a's activity

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

commented a paper about 6 hours ago

Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?

Paper • 2610.38342 • Published 3 days ago • 9 •

3

commented a paper 1 day ago

TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents

Paper • 2610.30161 • Published about 1 month ago • 10 •

3

commented a paper 2 days ago

Multiscale Policy Optimization for Long-Horizon LLM Agents

Paper • 2610.35013 • Published 5 days ago • 383 •

4

commented a paper 3 days ago

Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5

Paper • 2610.33732 • Published 7 days ago • 9 •

10

commented a paper 4 days ago

DISC: Domain-Integrated Similarity Cost for Time-Series Dataset

Paper • 2610.31288 • Published 9 days ago • 8 •

3

commented a paper 5 days ago

Diffusion Language Models Change Speed Across Tasks and Languages

Paper • 2610.25835 • Published 12 days ago • 24 •

2

commented a paper 6 days ago

Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems

Paper • 2610.30418 • Published 10 days ago • 27 •

11

commented a paper 7 days ago

What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models

Paper • 2610.31576 • Published 9 days ago • 13 •

3

commented a paper 8 days ago

From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks

Paper • 2610.28027 • Published 11 days ago • 14 •

4

commented a paper 9 days ago

FlowState: Execution State as Memory for Long-Horizon LLM Agents

Paper • 2609.34565 • Published 23 days ago • 24 •

4

commented a paper 10 days ago

Token-Set Choice Confounds POPE: A Systematic Audit of Yes/No Extraction in VLM Hallucination Evaluation

Paper • 2610.25964 • Published 12 days ago • 4 •

4

commented a paper 11 days ago

Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models

Paper • 2610.22428 • Published 16 days ago • 21 •

4

commented a paper 14 days ago

When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill

Paper • 2610.21500 • Published 16 days ago • 4 •

3

commented a paper 16 days ago

EMHO: EMbodied Agent Harness Optimization via Experience Traces

Paper • 2610.08432 • Published 25 days ago • 11 •

4

commented a paper 18 days ago

When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better

Paper • 2610.11291 • Published 23 days ago • 29 •

3

commented a paper 19 days ago

Incidental information contaminates patient notes and disrupts clinical reasoning in large language models

Paper • 2610.08585 • Published 25 days ago • 7 •

3

commented a paper 20 days ago

Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub

Paper • 2610.11169 • Published 23 days ago • 8 •

3

commented a paper 21 days ago

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

Paper • 2610.11794 • Published 23 days ago • 48 •

5

commented a paper 22 days ago

A self-learning scientific agent for X-ray diffraction

Paper • 2610.07862 • Published 25 days ago • 19 •

6

commented a paper 23 days ago

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

Paper • 2610.00417 • Published about 1 month ago • 2 •

4