Inference-Time Amplification of Weak Reasoning Models
Research
Research News
New papers, breakthroughs and academic AI research
Who Checks the Citations? Benchmarking Legal Hallucination Detection
Research
InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models
Research
Towards Subject-Oriented Video Captioning via User-Specified Targets
Research
Differentially Private Mixing of Public Datasets Improves Private Learning
Research
BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents
Research
Neutral Substrates: A Design Constraint for Shared Records Under Persistent Interpretive Disagreement
Research
Mind the Drift: Diagonal Linear Networks Under Large Learning Rates
Research
Co-Optimizing Graph Sparsification and Approximate Computing for Energy-Efficient FPGA-Based GCN Inference
Research
TIGER: Time-Series Classification with In-Context-Learning Gated Ensemble of Representations
Research
Structured Representation Learning for Behavior Cloning: How can we learn to safely control a nuclear power plant?
Research
MatrixFormer: A Foundation Model for Matrix Completion
Research