News
AI, cybersecurity, machine learning, scraping & programming news.
76 results on this page · clear filters
Copy the Same, Distill the Difference: Initializing Linear Vision Transformers
Linear Vision Transformers (ViTs) aim to replace the softmax attention mechanism with a linear-complexity alternative, enabling more efficient token routing at scale. However, a persistent obstacle is that linear ViTs typically re...
New LoRA Skills Should Read but Never Write
Large language models implicitly infer attributes of their users and adjust their behavior accordingly, yet these internal user models remain difficult to inspect and causally manipulate. A team from the Technical University of Mu...
OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation
When Video Generation Needs to Listen to More Than Words Text-to-video models have gotten good at translating prompts into motion. But professional creative work rarely starts from a blank slate. A designer hands you a character s...
Available Guardrails: Certifying Selective Prediction across ML Systems
The Safety Gate That Can't Get a Certificate Modern AI systems hide a quiet failure mode. A model may be perfectly capable, but the deployment team cannot prove it. The problem surfaces when a selective predictor, one that outputs...
$λ$-Controlled GRPO: Turning Flow-Matching Ratio Instability into a Budgeted Resource
The Instability Problem in Flow-Matching RL for Image Generation Reinforcement learning has become the standard tool for aligning language models with human preferences, and it is now extending rapidly to image generation. The cor...
COMPLEX: A Closed-Form Certified Embedding of Multiparameter Persistence Modules
Why Every Multiparameter Persistence Feature Map Lies About Its Geometry Topological data analysis extracts shape from data: clusters, loops, voids, and their higher-dimensional analogs. The standard tool is persistent homology, w...
Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention
Why Value Gating Works in Attention Has Been a Blind Men and the Elephant Problem Gating the value pathway of attention has become a popular trick in language model pretraining. A series of recent papers report that adding a learn...
Embedding Models Measure in Peculiar Ways
When you type "2 kilometers" and "2000 meters" into a sentence embedding model, the cosine similarity between them should be nearly 1.0. After all, they denote the same physical quantity. A well-functioning semantic measurement sp...
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...
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...