Avi

avahal's activity

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

commented 9 papers 2 days ago

CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion

Paper • 2601.09512 • Published 8 days ago • 3 •

3

YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation

Paper • 2601.08441 • Published 9 days ago • 7 •

3

SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature

Paper • 2601.10108 • Published 7 days ago • 6 •

3

The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models

Paper • 2601.10387 • Published 7 days ago • 9 •

2

Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation

Paper • 2601.10880 • Published 7 days ago • 15 •

4

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Paper • 2601.11061 • Published 6 days ago • 7 •

3

CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation

Paper • 2601.11096 • Published 6 days ago • 6 •

3

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge

Paper • 2601.08808 • Published 9 days ago • 34 •

4

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development

Paper • 2601.11077 • Published 6 days ago • 61 •

4

commented 11 papers 3 days ago

More Images, More Problems? A Controlled Analysis of VLM Failure Modes

Paper • 2601.07812 • Published 10 days ago • 5 •

3

PhyRPR: Training-Free Physics-Constrained Video Generation

Paper • 2601.09255 • Published 8 days ago • 2 •

3

Language of Thought Shapes Output Diversity in Large Language Models

Paper • 2601.11227 • Published 6 days ago • 4 •

3

AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems

Paper • 2601.11354 • Published 6 days ago • 3 •

3

Entropy Sentinel: Continuous LLM Accuracy Monitoring from Decoding Entropy Traces in STEM

Paper • 2601.09001 • Published 9 days ago • 15 •

3

PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models

Paper • 2601.11087 • Published 6 days ago • 9 •

3

ShapeR: Robust Conditional 3D Shape Generation from Casual Captures

Paper • 2601.11514 • Published 6 days ago • 16 •

3

Building Production-Ready Probes For Gemini

Paper • 2601.11516 • Published 6 days ago • 6 •

3

PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records

Paper • 2601.09636 • Published 8 days ago • 6 •

4

Reasoning Models Generate Societies of Thought

Paper • 2601.10825 • Published 7 days ago • 10 •

3

FrankenMotion: Part-level Human Motion Generation and Composition

Paper • 2601.10909 • Published 7 days ago • 17 •

3