Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers have developed ProHiFlo, a hierarchical flow matching framework for de novo protein generation that models backbone geometry before refining to all-atom coordinates, reducing computational cost while maintain…
A new perspective argues that generative AI models for semiconductor manufacturing must enforce hard physical constraints by design, not through post-hoc filtering, because physically invalid outputs are unusable in fabr…
Researchers have developed MF-Net, a recurrent dynamical model that represents all variables in a shared field state and updates it through a learned mechanical transition, enabling both forecasting and structural readou…
Researchers at an undisclosed institution backpropagated a steady-state loss through unrolled Gray-Scott simulation to recover reaction-diffusion parameters, finding that optimization fails due to flat plateaus and sharp…
A new study from researchers testing adapter composition in large language models found that geometry-aware merging strategies, which enforce orthogonality or directional independence in parameter updates, provide no con…
A new study quantifies the rate at which undesirable behaviors transfer from teacher to student language models during distillation, a phenomenon known as subliminal learning. Researchers steered Llama-2-7B-Chat and Qwen…
Researchers have introduced Rotary Value Embeddings (RoVE), a parameter-free modification to Rotary Position Embeddings (RoPE) that makes value pathways position-sensitive by rotating values simultaneously with keys. Thi…
Researchers have developed a least-action-guided diffusion (LAPG) framework that enforces physical consistency in generative models during inference, addressing the challenge of reliable extrapolation beyond training dat…
Researchers introduced FreeBridge, a variational Schrödinger Bridge model that infers continuous cellular transition dynamics from high-content imaging assays where only endpoint populations are observable. By constraini…
Researchers have developed FlowBank, a three-stage framework that optimizes LLM-based multi-agent systems by precomputing a compact bank of reusable workflows and adaptively selecting among them per query. The approach a…
Neural networks maintain well-above-chance accuracy on classification tasks even when over 90% of input data is corrupted, far exceeding human recognition capabilities. Researchers analyzing multi-layer perceptrons under…
Researchers have developed Z-Image Turbo++, a two-step image generation model distilled from an eight-step teacher model, achieving high-fidelity results through three targeted design choices. The method uses teacher-gen…
Researchers have identified three critical limitations in existing preference optimization methods for medical Large Vision-Language Models (LVLMs), including their inability to distinguish clinically critical tokens fro…
Researchers have developed Context-Centric Feature Fusion (CCFF), a framework that uses two attention-based modules to improve detection of co-occurring objects in autonomous driving. The system achieved a Category-level…
Researchers introduced Efficient Continual Alignment (ECA), a new exemplar-free incremental learning approach for open-ended image-to-text generation that adapts alignment modules within pre-trained vision-language model…
Researchers have developed CD-RCM, the first novel-view synthesis approach specifically for reflectance confocal microscopy (RCM), enabling continuous-depth visualization of human skin from sparse, anisotropic z-stacks. …
Researchers have developed VLADriveBench, a new evaluation framework that assesses whether the chain-of-thought reasoning produced by vision-language-action (VLA) models for autonomous driving is relevant and causally co…
Researchers introduced GRIP, a feedback-guided retrieval framework for multimodal in-context learning that selects examples based on their actual impact on model predictions rather than visual similarity. The system impr…
Researchers introduced PERIA, a tool-augmented visual agent designed to improve spatial reasoning in vision-language models by actively acquiring evidence and performing multi-step visual interactions. The agent uses two…
Researchers have developed L-VARC, a novel framework that enhances visual reasoning on the Abstraction and Reasoning Corpus (ARC) by integrating a language-guided Learning Using Privileged Information (LUPI) branch. The …