11 posts published in the last hour
- 20:32Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering
- 20:32TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
- 20:32GEM: A Generative Embedding Model Bridging Reasoning and Retrieval
- 20:31NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video
- 20:31LipCache: A Local Inference Proxy with Certified Caching for Edge Image Classification Service
- 20:03LOB-ID: Evaluating Synthetic Market Data by Inception Distances
- 20:03Sampling Luck Masquerades as Allocation Gain: Auditing Test-Time Budget Allocation for Neural Combinatorial Optimization
- 20:03EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory
- 20:03TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes
- 20:03How kids feel about AI, in their own words
- 20:03LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation
