LIVE-Last scan updating-53 sources active-870 signals today-RESEARCH PVBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Topic intelligence

Cross-source radar trends, not isolated headlines.

Topics connect real clusters, entities, source mix, and published decisions. Empty states are real; no trend is invented when the signals are not strong enough yet.

Topics
8,145
current graph
Top trend
56
CorporateBench: A New Benchmark for LLM Q&A on Enterprise Data
TopicCategorySignalsMomentumLast seenTrend
CorporateBench: A New Benchmark for LLM Q&A on Enterprise Data
CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases
Benchmarks273Aug 28, 2026RDR56
TTPO: Test-Time Policy Optimization
TTPO: Test-Time Policy Optimization
Research Papers273Aug 28, 2026RDR56
Property-Specific Recoverability from Contact PPG to Camera rPPG under Heterogeneous Observation Conditions
Property-Specific Recoverability from Contact PPG to Camera rPPG under Heterogeneous Observation Conditions
Research Papers273Aug 28, 2026RDR56
RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature
RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature
Benchmarks273Aug 28, 2026RDR56
LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
Research Papers273Aug 28, 2026RDR56
CAST: Concept-Guided Artifact Suppression Tuning for Auditable Clinical Language Models
Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction
Research Papers273Aug 28, 2026RDR56
Danbooru RAG v2 Dataset for Improved LLM Performance
patvessel/danbooru-rag-v2, patvessel/danbooru-rag-G-v3, patvessel/danbooru-rag-v3, patvessel/danbooru-rag-G-v2
RAG & Search565May 29, 2026RDR56
Scalable GNN for Friend Recommendation
Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling
Research Papers273Aug 28, 2026RDR56
CLAP: Cross-Embodiment Video World Models for Zero-Shot Physical Simulation
CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators
Research Papers273Aug 28, 2026RDR56
MILO: Large Reconstruction Models for 3D Human-Object Interaction
Reconstructing Humans and Objects in Interaction using Large Reconstruction Models
Research Papers273Aug 28, 2026RDR56