Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
Paper • 2604.04934 • Published • 27 •
4
Avi
avahal
AI & ML interests
LLMs
Recent Activity
commentedon a paper about 4 hours ago
Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision commentedon a paper about 4 hours ago
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning commentedon a paper about 4 hours ago
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code GenerationOrganizations
None yet
commented 6
papers about 4 hours ago
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
Paper • 2604.05404 • Published • 26 •
3
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
Paper • 2604.03922 • Published • 41 •
3
Learning to Retrieve from Agent Trajectories
Paper • 2604.04949 • Published • 50 •
4
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
Paper • 2604.06132 • Published • 88 •
3
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Paper • 2604.05015 • Published • 191 •
6
commented 12
papers 1 day ago
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
Paper • 2604.04911 • Published • 28 •
3
AURA: Always-On Understanding and Real-Time Assistance via Video Streams
Paper • 2604.04184 • Published • 41 •
3
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Paper • 2604.04921 • Published • 78 •
4
LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
Paper • 2603.28301 • Published • 74 •
5
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Paper • 2604.04771 • Published • 97 •
4
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Paper • 2604.04707 • Published • 162 •
12
Communicating about Space: Language-Mediated Spatial Integration Across Partial Views
Paper • 2603.27183 • Published • 15 •
3
Test-Time Scaling Makes Overtraining Compute-Optimal
Paper • 2604.01411 • Published • 19 •
4
Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?
Paper • 2604.03016 • Published • 27 •
3
Token Warping Helps MLLMs Look from Nearby Viewpoints
Paper • 2604.02870 • Published • 26 •
4
A Simple Baseline for Streaming Video Understanding
Paper • 2604.02317 • Published • 65 •
6
Self-Distilled RLVR
Paper • 2604.03128 • Published • 134 •
5
commented 2
papers 6 days ago