Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training
Research
Research News
New papers, breakthroughs and academic AI research
How Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis
Research
Pre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus Dataset
Research
Automatically Building and Updating a Knowledge Graph of MLIP Models
Research
MeshSIPP: Efficient Lattice Planning in Dynamic Environment
Research
Reasoning-Token Spikes Under Prompted Untruthful Responding in Large Language Models
Research
SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions
Research
Learning to Report Unsafe Tasks in a Multi-Agent Game
Research
UniCSI Towards a Universal Wi-Fi CSI Encoder for Ubiquitous Human Sensing
Research
MoR-MLLM: Mixture of Recursions for Efficient Multimodal Large Language Models
Research
CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution
Research
One-Slide Calibration of Pathology Foundation Models
Research