Scientists get a first look at the innermost region of a white dwarf system
X-ray observations reveal surprising features of the dying star’s most energetic environment.
Archives AI News
VisPlay: Self-Evolving Vision-Language Models from Images
arXiv:2511.15661v1 Announce Type: cross Abstract: Reinforcement learning (RL) provides a principled framework for improving Vision-Language Models (VLMs) on complex reasoning tasks. However, existing RL approaches often rely on human-annotated labels or task-specific heuristics to define verifiable rewards, both of which…
Differentiable, Bit-shifting, and Scalable Quantization without training neural network from scratch
arXiv:2510.16088v3 Announce Type: replace-cross Abstract: Quantization of neural networks provides benefits of inference in less compute and memory requirements. Previous work in quantization lack two important aspects which this work provides. First almost all previous work in quantization used a…
Decentralized Gaussian Process Classification and an Application in Subsea Robotics
arXiv:2511.15529v1 Announce Type: cross Abstract: Teams of cooperating autonomous underwater vehicles (AUVs) rely on acoustic communication for coordination, yet this communication medium is constrained by limited range, multi-path effects, and low bandwidth. One way to address the uncertainty associated with…
$pi^{*}_{0.6}$: a VLA That Learns From Experience
arXiv:2511.14759v2 Announce Type: replace Abstract: We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP), that provides for RL training of…
Operator learning for energy-efficient building ventilation control with computational fluid dynamics simulation of a real-world classroom
arXiv:2504.21243v2 Announce Type: replace-cross Abstract: Energy-efficient ventilation control plays a vital role in reducing building energy consumption while ensuring occupant health and comfort. While Computational Fluid Dynamics (CFD) simulations provide detailed and physically accurate representation of indoor airflow, their high…
Energy-based generator matching: A neural sampler for general state space
arXiv:2505.19646v3 Announce Type: replace Abstract: We propose Energy-based generator matching (EGM), a modality-agnostic approach to train generative models from energy functions in the absence of data. Extending the recently proposed generator matching, EGM enables training of arbitrary continuous-time Markov processes,…
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
arXiv:2509.24006v2 Announce Type: replace Abstract: In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We find that attention weights can be separated into two…
It’s LIT! Reliability-Optimized LLMs with Inspectable Tools
arXiv:2511.14903v1 Announce Type: new Abstract: Large language models (LLMs) have exhibited remarkable capabilities across various domains. The ability to call external tools further expands their capability to handle real-world tasks. However, LLMs often follow an opaque reasoning process, which limits…
Structured Contrastive Learning for Interpretable Latent Representations
arXiv:2511.14920v1 Announce Type: new Abstract: Neural networks exhibit severe brittleness to semantically irrelevant transformations. A mere 75ms electrocardiogram (ECG) phase shift degrades latent cosine similarity from 1.0 to 0.2, while sensor rotations collapse activity recognition performance with inertial measurement units…