Sam Vega

svega85's activity

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

upvoted a paper about 3 hours ago

Evidence-Grounded Auditing of Identification Assumptions in Climate-Policy Causal Evaluations

Paper • 2609.30867 • Published 6 days ago • 4

upvoted a paper 3 days ago

Blaming Across the Aisle: Political Contrasting and Blame Attribution in the Danish Parliament

Paper • 2609.26346 • Published 9 days ago • 11

upvoted a paper 5 days ago

From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health

Paper • 2609.25186 • Published 10 days ago • 32

upvoted a paper 6 days ago

1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation

Paper • 2609.24432 • Published 10 days ago • 16

upvoted a paper 8 days ago

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2609.20784 • Published 14 days ago • 57

upvoted 2 papers 9 days ago

ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models

Paper • 2609.18487 • Published 15 days ago • 47

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

Paper • 2609.17708 • Published 16 days ago • 77

upvoted a paper 10 days ago

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published 17 days ago • 215

upvoted a paper 11 days ago

PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control

Paper • 2609.17521 • Published 16 days ago • 10

upvoted a paper 13 days ago

Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training

Paper • 2609.15051 • Published 17 days ago • 14

upvoted 2 papers 15 days ago

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

Paper • 2609.05903 • Published 26 days ago • 65

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

Paper • 2609.10715 • Published 22 days ago • 331

upvoted a paper 16 days ago

Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents

Paper • 2609.09219 • Published 24 days ago • 16

upvoted a paper 18 days ago

RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning

Paper • 2609.03199 • Published 29 days ago • 31

upvoted a paper 19 days ago

Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM

Paper • 2609.04098 • Published 28 days ago • 85

liked a model 19 days ago

linkred/stock_prediction_v5

Updated Oct 19, 2024 • 8 • 8

upvoted a paper 19 days ago

SynthGait-19K: A Physically Grounded Synthetic Video Dataset for Gait Parameter Estimation

Paper • 2609.08108 • Published 23 days ago • 18

upvoted a paper 20 days ago

FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

Paper • 2609.03241 • Published 28 days ago • 54

liked 2 models 21 days ago

PeytonT/paper-link-prediction

Text Classification • 0.1B • Updated Jul 5 • 18 • 9

linkred/stock_prediction_v2_mini

Updated Nov 13, 2024 • 10 • 11