Task-Efficient Agent Evaluation Using Cached Traces
Research
Research News
New papers, breakthroughs and academic AI research
Rules, Traces and Routing Statistics: Training and Calibration Data for Open Models on ARC-AGI-2
Research
BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories
Research
SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding?
Research
GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization
Research
SpecCompact: Accelerating LLM Agent Context Compaction with Slot-Parallel Semantic Speculative Verification
Research
STARE: Scene Text-Aware multimodal Retrieval for Everyday objects
Research
Unlocking Turing Tensor Cores: A Measured Throughput Account of From-Scratch Pre-training on a Single 22G RTX 2080 Ti
Research
Drift-adaptive Representation Preservation for Domain-Incremental Learning
Research
ReactWorld: Structuring Interaction Responses for Embodied Video Generation
Research
The Male Abstraction Bias in Internet Culture and Large Language Models
Research
Text-Only Domain Adaptation for Low-Resource Medical ASR: Shallow Fusion and Density Ratio Rescoring for Hausa
Research