ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents
Research
Research News
New papers, breakthroughs and academic AI research
SAGA: Stable Acceleration Guidance for Autoregressive Video Generation
Research
Decentralized Multi-Agent Systems with Shared Context
Research
Pepti-drift: Scalable Safe-Active Peptide Generation Without Inference-Time Guidance
Research
More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe
Research
Design and Implementation of a Kalman Filter-Infused Algorithm for Tilt Estimation
Research
Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning
Research
BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models
Research
TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning
Research
CoFiE: Coarse-to-Fine Evidence Selection for Efficient Streaming Video Understanding
Research
Weighted Data Selection: Sharp Upper-Half and Five-Dimensional Laws
Research
What Do Scan-Derived Class Prototypes Add? Disentangling Supervision, Prototype Content and Query Protocol in Recognition over Frozen Foundation Features
Research