News
AI, cybersecurity, machine learning, scraping & programming news.
214 results on this page · clear filters
OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher
Post-Training Driving Policies Without Rendering Every Step End-to-end driving policies are pre-trained with behavior cloning on human demonstrations, mapping raw sensor data to actions or waypoint trajectories. This works in open...
RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents
Why Troubleshooting Agents Need Stateful Retrieval, Not Static Document Lookup Enterprise customer support tickets do not resolve in a single shot. They unfold across stages: a symptom report, hypothesis formation, iterative log i...
MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving
Getting RL Policies Off the Simulator and Onto Real Dirt Reinforcement learning promises superhuman autonomous driving, but nearly every RL policy that works in simulation collapses when transferred to a real vehicle. The gap is e...
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
Why Video Diffusion Hits a Wall at Long Sequences Video diffusion transformers process spatiotemporal token sequences that grow with both spatial resolution and temporal duration. A 14.3-second, 768p video produces thousands of la...
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
The Default Training Recipe for Language Agents Has a Hidden Blind Spot When you fine-tune a language model on agent trajectories, the training loss is applied only to the tokens the agent wrote. The environment responses, termina...
Should This Case Be Adapted? Prediction Fragmentation Controls Test-Time Adaptation
The Hidden Problem With Test-Time Adaptation When a medical image segmentation model encounters a new scan from a different hospital or scanner, test-time adaptation (TTA) can help recover accuracy lost to distribution shift. The...
How to Write with an LLM
There is a wrong way to use an LLM for writing, and a right one. The wrong way is to let the model generate your prose. The right way is to write everything yourself, then hand the draft to a model and let it find the problems you...
Show HN: Die With Me – Claude and Codex rate limits as AIM away messages
Die With Me Turns AI Token Limits Into a Social Experience Running out of tokens used to be a solitary frustration. You hit your Claude Code limit mid-refactor, stared at the error message, and waited. Now there is an app that tur...
A Zeroth-Order Paradigm for LLM Preference Alignment
The Likelihood Displacement Problem in Preference Alignment Training large language models to follow human preferences has become a core bottleneck in shipping reliable AI systems. Reinforcement learning from human feedback (RLHF)...
AgentLSD: Evaluating AI Security Agents Under Adversarial Task Contamination
When Security Agents Meet Deceptive Environments AI agents that handle security tasks do not operate in clean, trustworthy environments. They browse web pages, parse source code, read log files, and inspect configuration output. E...