Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
Paper • 2605.05922 • Published • 4 •
2
Avi
avahal
AI & ML interests
LLMs
Recent Activity
commentedon a paper 9 days ago
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling commentedon a paper 9 days ago
TIDE: Every Layer Knows the Token Beneath the Context commentedon a paper 9 days ago
BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language ModelsOrganizations
None yet
commented 20
papers 9 days ago
TIDE: Every Layer Knows the Token Beneath the Context
Paper • 2605.06216 • Published • 8 •
3
BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models
Paper • 2605.05758 • Published • 4 •
3
EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions
Paper • 2602.00095 • Published • 3 •
3
Recovering Hidden Reward in Diffusion-Based Policies
Paper • 2605.00623 • Published • 4 •
3
The Scaling Properties of Implicit Deductive Reasoning in Transformers
Paper • 2605.04330 • Published • 5 •
3
KernelBench-X: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels
Paper • 2605.04956 • Published • 7 •
4
When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels
Paper • 2605.06652 • Published • 5 •
3
Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
Paper • 2605.06535 • Published • 3 •
3
Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
Paper • 2605.06643 • Published • 4 •
3
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
Paper • 2605.05242 • Published • 107 •
3
The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models
Paper • 2605.06196 • Published • 7 •
3
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
Paper • 2605.06638 • Published • 14 •
5
AI Co-Mathematician: Accelerating Mathematicians with Agentic AI
Paper • 2605.06651 • Published • 15 •
3
Audio-Visual Intelligence in Large Foundation Models
Paper • 2605.04045 • Published • 32 •
3
RemoteZero: Geospatial Reasoning with Zero Human Annotations
Paper • 2605.04451 • Published • 8 •
3
SkillOS: Learning Skill Curation for Self-Evolving Agents
Paper • 2605.06614 • Published • 42 •
3
SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation
Paper • 2605.06356 • Published • 5 •
4
TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding
Paper • 2605.04962 • Published • 8 •
3
ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
Paper • 2605.04647 • Published • 9 •
3