Opening the Black Box of Classifier-Free Guidance via Information Bottleneck
Information bottleneck analysis explains classifier-free guidance activation timing in diffusion models, replacing heuristic schedules with principled theory.
Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
Information bottleneck analysis explains classifier-free guidance activation timing in diffusion models, replacing heuristic schedules with principled theory.
PDE-PFN applies prior-data fitted networks to PDE solving via in-context learning, using self/cross-attention for posterior predictive inference.
SBNO uses diffusion Schrödinger bridge matching for PDE surrogate modeling with sparse, partial observations and unknown physics constraints.
We introduce MORAD, an online reinforcement learning framework for backbone-conditioned RNA diffusion models that trains a single shared policy across diverse target backbones. Structure-conditioned RNA inverse design seeks nucleotide sequences compatible with a target…
Ben Affleck is going viral for his deep knowledge of AI, from neural networks and transformers to open weights. The actor, who sold his AI filmmaking startup to Netflix earlier this year, is proving he's more than just a Hollywood star.
USA Today Co., along with the several local newspapers it owns, is suing OpenAI over claims that the company copied "hundreds of thousands" of articles to train its AI models, as reported earlier by Reuters. In a filing on Thursday, the publisher asks for damages of more than…
If Elon Musk and SpaceXAI were going to back any Linux distro, it seems obvious they'd back Omarchy. Today it was announced that SpaceXAI would be joining the Omacom Foundation, which oversees Omarchy, as a Founding Corporate Patron and donating $1.5 million worth of Grok…
RoboRSI system enables robot self-improvement by refining learned skills from execution feedback, organizing repairs by task structure for reuse.
Global-regional alignment method enables kilometer-scale weather forecasting by reusing pretrained global models to guide high-resolution local predictions.
AAArena benchmark evaluates Adversarial Heuristic Learning paradigm where agents refine game policies via executable code without weight updates.
ContiLNN augments 2D medical image restoration with continuous-time liquid neural modules for cross-slice anatomical continuity modeling.
RiCo models rigid-body contact via local surface neighborhoods rather than end-to-end scene prediction, improving physics simulation accuracy.
Theoretical analysis of oracle complexity for nonsmooth nonconvex composite optimization including neural network training.
LLM agents selecting PDE neural operator fine-tuning configurations outperform Bayesian optimization, with causal analysis of feedback vs. prior usage.
DeltaReplay enables mobile GUI agents to selectively reuse execution trajectories from memory by matching task-relevant steps without forcing irrelevant guidance.
Benchmarks 18 neural architectures on 10 temporal pattern recognition tasks for robotic gesture control across 250+ experimental configurations.
Consensus pseudo-label learning improves reliability by constructing complementary decision sources via graph structure variation and node coassignment.
AgentEvolver enables agents to develop reusable capabilities during task execution while keeping foundation models fixed.
NeuralBES: differentiable physics-informed neural emulator for building energy simulation bridging high-fidelity calibration and data-driven scalability.
Seq-Flow: conditional flow model for probabilistic forecasting that reuses prior distributions via ODE transport, reducing sampling cost with improved few-step accuracy.
Cross-domain pretraining improves neural CFD surrogates' generalization across geometries and engineering applications.
Google DeepMind, Meta, and AI drug discovery startup Isomorphic Labs are jointly investing $300 million into Biohub, the nonprofit biomedical research organization founded by Mark Zuckerberg and his wife, Priscilla Chan, as reported by Reuters. The funding is part of a $1.8…
From Nvidia and Chime to Obvious Ventures and Anthropic, explore the entire roundtable agenda at TechCrunch Disrupt 2026. Register now to save up to $100 on your pass and get a second pass at 50% off.
Physics-informed neural cellular automata learn traffic flow dynamics from data while preserving physical constraints.
NeuralZip reuses statistical structures across model weights to improve lossless compression via shared Huffman codes and packed exponents.
QCATS enables sparse Transformer inference in databases by exposing query context and relational metadata to neural execution planning.
Bayesian neural networks learn which parameters should be stochastic via deep weight factorization, sparsifying stochasticity rather than capacity.
CoNN-AL framework for data-efficient inverse design in automotive engineering using stream-based active learning and uncertainty estimation.
Mean field theory characterizes fluctuations of nonlinear observables in wide shallow networks trained via SGD.
Like other solutions, it is not especially reliable, and easy to circumvent.