Gabriel Almeida

gabi-a's activity

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

upvoted a paper about 19 hours ago

Thinking Inertia: LLMs Keep Thinking When Told Not To

Paper • 2610.11765 • Published 8 days ago • 245

upvoted 2 papers 4 days ago

CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use

Paper • 2610.09127 • Published 10 days ago • 22

Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position

Paper • 2610.10114 • Published 9 days ago • 33

upvoted 2 papers 6 days ago

OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning

Paper • 2610.02181 • Published 15 days ago • 28

HuatuoGPT-3: RL-Only Domain Adaptation from Base Models

Paper • 2610.05966 • Published 11 days ago • 47

upvoted a paper 7 days ago

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

Paper • 2610.07767 • Published 10 days ago • 93

upvoted a paper 8 days ago

ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience

Paper • 2610.05303 • Published 12 days ago • 24

upvoted a paper 9 days ago

Does Learning Protein Folding Generalize to Broader Reasoning?

Paper • 2609.38879 • Published 16 days ago • 63

upvoted 4 papers 10 days ago

AutoDataBench: A Data-centric Testbed for Accelerating Auto Research

Paper • 2609.40097 • Published 16 days ago • 50

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 15 days ago • 111

EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos

Paper • 2609.39378 • Published 16 days ago • 74

Video Generation Models: A Survey of Post-Training and Alignment

Paper • 2610.00812 • Published 16 days ago • 63

upvoted a paper 11 days ago

Unmask the State: When Does State Adaptation Matter for Masked Diffusion Language Models

Paper • 2609.33355 • Published 19 days ago • 51

upvoted a paper 12 days ago

All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation

Paper • 2609.27901 • Published 23 days ago • 24

upvoted a paper 13 days ago

MassAlloc Attention: Let Attention Allocate Its Own Compute

Paper • 2609.32712 • Published 20 days ago • 75

upvoted a paper 14 days ago

OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?

Paper • 2609.38079 • Published 17 days ago • 57

upvoted 3 papers 15 days ago

Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents

Paper • 2609.33772 • Published 19 days ago • 36

TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

Paper • 2609.33295 • Published 19 days ago • 72

Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation

Paper • 2609.35347 • Published 18 days ago • 110

upvoted a paper 16 days ago

Block Sparse Attention with Log-Linear Complexity

Paper • 2609.31093 • Published 21 days ago • 30