Improved Distributional Diffusion Models
arXiv:2609.37147v1 Announce Type: new Abstract: Distributional Diffusion Models (DDMs) replace the standard mean-prediction denoiser with a distributional denoiser trained via a scoring rule objective
Knowledge catalogue
arXiv:2609.37147v1 Announce Type: new Abstract: Distributional Diffusion Models (DDMs) replace the standard mean-prediction denoiser with a distributional denoiser trained via a scoring rule objective
arXiv:2609.36214v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used by people whose first language is not English, yet these users have been shown to receive systematica
arXiv:2609.37156v1 Announce Type: cross Abstract: World models enable agents to learn and plan in imagination, but predictions beyond their experience can become unreliable and mislead decisions. Exis
arXiv:2609.36264v1 Announce Type: new Abstract: Reliable evaluation of large language models (LLMs) is essential for their development and deployment, yet is often costly, risky, and difficult to perf
arXiv:2609.36561v1 Announce Type: new Abstract: Motion planning on arbitrary Riemannian manifolds is an important and difficult problem that frustrates typical planning methods for Euclidean spaces. I
arXiv:2609.37004v1 Announce Type: new Abstract: We present World2Motion, a framework that generates scene-aware 3D human motion and corresponding video from a single image and a text prompt. While exi
arXiv:2609.29902v1 Announce Type: cross Abstract: A new proposal called DM-SMC (Diffusion Model - Sequential Monte Carlo) is investigated, which samples ensembles defined in terms of an action, using
arXiv:2609.34083v1 Announce Type: new Abstract: Recommendation models with sparse embeddings and a shared consumer often exhibit the one-epoch phenomenon: a second epoch lowers training loss while sha
arXiv:2609.33178v1 Announce Type: new Abstract: Molecularly guided pathology foundation models (PFMs) exploit transcriptomic or proteomic information to enrich whole-slide image (WSI) representations,
arXiv:2609.33114v1 Announce Type: cross Abstract: For decades, statistical inference has largely been developed one problem at a time. Given a scientific target, such as a treatment effect or a regres
arXiv:2609.32062v1 Announce Type: cross Abstract: Although E[dropout(x)] = x, here we show that E[LayerNorm(dropout(x))] is not equal to LayerNorm(x). Accordingly, the pattern of a Dropout layer follo
arXiv:2609.34742v1 Announce Type: new Abstract: Recent studies suggest that large language models encode emotion concepts as structured internal representations, but most existing work focuses on text
arXiv:2609.34921v1 Announce Type: new Abstract: Predicting Drug-Target Interactions~(DTIs) is a central task in computational drug discovery, with direct applications in virtual screening, drug repurp
arXiv:2609.33172v1 Announce Type: cross Abstract: World-Action models (WAMs) trained on static demonstrations often fail to manipulate moving targets even when they possess the required manipulation s
arXiv:2609.33086v1 Announce Type: new Abstract: Current approaches to aligning language models often make it hard to know what behavior is being rewarded or to change that reward in a targeted way. In
arXiv:2609.34809v1 Announce Type: new Abstract: Vision-language models (VLMs) can answer simple visual questions, but often struggle when one question requires several visual judgments. We study this
arXiv:2609.34362v1 Announce Type: new Abstract: World Action Models (WAMs) augment robot action generation with future visual supervision. Existing WAMs commonly fuse main and wrist observations into
arXiv:2609.35545v1 Announce Type: new Abstract: Epidemic policy planning often requires coordination between geographical regions, taking into account mobility-driven spillovers and how to make use of
arXiv:2609.33965v1 Announce Type: cross Abstract: We describe a methodology for estimating the per-token energy cost of cloud-hosted large language model (LLM) inference, separating between input (pre
arXiv:2609.35767v1 Announce Type: new Abstract: Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong,
arXiv:2607.17511v2 Announce Type: replace Abstract: Large Time Series Foundation Models (TSFMs) demonstrate strong zero-shot forecasting capabilities across diverse domains. However, their application
arXiv:2609.33563v1 Announce Type: new Abstract: World models improve sample efficiency by training policies on imagined trajectories, but their usefulness depends on learning representations that capt
arXiv:2609.32470v1 Announce Type: new Abstract: Large reasoning models (LRMs) often suffer from overconfidence when expressing their uncertainty. Confidence-aware reinforcement learning (RL) offers a
arXiv:2609.34021v1 Announce Type: new Abstract: Test-Time Training (TTT) adapts models to incoming test samples (e.g. out-of-distribution, (OOD)) when conventional fine-tuning is infeasible. Existing
arXiv:2609.31862v1 Announce Type: cross Abstract: Reconstruction and simulation at a collider experiment are long chains of specialised algorithms, each tuned to a single step. We explore how one mode
arXiv:2609.32141v1 Announce Type: new Abstract: Deep ReLU networks are piecewise-affine mappings that partition the input space into cells, each characterized by a distinct activation pattern. This st
arXiv:2609.35405v1 Announce Type: new Abstract: Pretrained 2D foundation models offer a practical alternative to dedicated 3D pretraining for brain structural magnetic resonance imaging (sMRI), but th
arXiv:2609.34044v1 Announce Type: new Abstract: Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pr
arXiv:2609.33947v1 Announce Type: cross Abstract: Diffusion language models (DLMs) promise fast parallel generation, yet high-quality samples often require large number of refinement steps, which dimi
arXiv:2609.32831v1 Announce Type: new Abstract: Unified multimodal models combine understanding, generation, and editing within a single network, offering a promising foundation for versatile multimod
arXiv:2609.35322v1 Announce Type: new Abstract: Score-based generative models generate new samples by integrating a time-dependent drift that carries Gaussian noise onto the target distribution. In pr
arXiv:2609.31685v1 Announce Type: new Abstract: Diffusion language models (DLMs) enable flexible, parallel generation, but their iterative denoising remains computationally expensive, motivating incre
arXiv:2609.32124v1 Announce Type: new Abstract: When adapting pre-trained models through fine-tuning, freezing weights alone might not preserve performance, as updates elsewhere can change the inputs
arXiv:2609.33220v1 Announce Type: new Abstract: Outcome-based reinforcement learning can produce models with similar task performance but very different ways of communicating about their mistakes. We
arXiv:2609.31639v1 Announce Type: new Abstract: Diagnosing rolling-element bearing faults from vibration is a canonical physical-sensing task and a widely used benchmark for domain adaptation under op
arXiv:2609.34457v1 Announce Type: new Abstract: Transformer-based models are widely used for reasoning, coding, and multimodal agentic tasks. To provide formal assurance of desirable behaviors, such a
arXiv:2505.09738v2 Announce Type: replace-cross Abstract: Pretrained language models (LLMs) are often constrained by their fixed tokenization schemes, leading to inefficiencies and performance limitat
arXiv:2406.09896v3 Announce Type: replace Abstract: Achieving robust generalization across diverse data domains remains a significant challenge in computer vision. This challenge is important in safet
arXiv:2512.14253v4 Announce Type: replace Abstract: In this work, we introduce FLAME, a family of extremely lightweight and capable Time Series Foundation Models, which support versatile forecasting t
arXiv:2609.31383v1 Announce Type: cross Abstract: End-to-end driving policies are commonly trained through open-loop behavior cloning, yet they must ultimately operate in closed-loop when deployed on
AI Security Institute: In simulations, GPT-6 Astra conducted unsanctioned supply-chain attacks more often than earlier OpenAI models when prompted only to perform a cyber evaluation — Our new evaluati
We built state-of-the-art models for reading forms 📋 Form documents have the following properties that trip up VLMs: ✅ They carry much more structure than can be represented in standard markdown. You
Micha wrote “one of our models was able to gain unauthorized access to the internet during RL training” I love the use of the passive voice. Tis a subtle way to say “we humans at @OpenAI are essential
arXiv:2609.29092v1 Announce Type: cross Abstract: Vision-based legged locomotion methods assume clean depth at training time and rely on hand-tuned post-processing filters at deployment. However, filt
arXiv:2501.09223v3 Announce Type: replace-cross Abstract: This is a book about large language models. As indicated by the title, it primarily focuses on foundational concepts rather than comprehensive
arXiv:2609.28931v1 Announce Type: new Abstract: Driving world models provide a promising route toward scalable counterfactual data generation and interactive simulation beyond recorded driving logs. R
arXiv:2609.29073v1 Announce Type: new Abstract: Vision-Language Models (VLMs) describe scenes well but reason poorly about metric 3D structure such as absolute distances, physical sizes, or egocentric
arXiv:2609.27359v1 Announce Type: new Abstract: Vietnam's Personal Data Protection Law (Law No. 91/2025/QH15) and Decree No. 356/2025/ND-CP, effective January 1, 2026, require organizations to establi
arXiv:2609.27115v1 Announce Type: new Abstract: A face recognition model links two images of a person recorded on separate occasions when their embedding similarity exceeds an operating threshold. We
arXiv:2609.28258v1 Announce Type: cross Abstract: Robotic assembly in high-mixture settings requires adaptable systems that can handle diverse parts, yet current approaches typically rely on policies
arXiv:2511.17909v2 Announce Type: replace Abstract: Chemical reasoning inherently integrates visual, textual, and symbolic modalities, yet existing benchmarks rarely capture this complexity, often rel
arXiv:2609.25501v1 Announce Type: new Abstract: We present the first method for native, continuous gradient descent for machine learning models with p-adic parameters. Existing native optimizers are d
arXiv:2609.25014v1 Announce Type: cross Abstract: Organizations fine-tune small language models on private data and then compress them to 4 bits for resource-efficient deployment. We show that the com
arXiv:2609.25945v1 Announce Type: new Abstract: The field of Artificial Intelligence has been adopted for many application domains. Vision Language Models are one of the recently advanced AI technique
arXiv:2609.26561v1 Announce Type: cross Abstract: We present an improvement on previous spacecraft pose estimation architectures that results in the lowest published mean rotation errors we know of on
arXiv:2609.23478v1 Announce Type: new Abstract: Latent action models infer a code for the transition between two frames of action-free video. Recent methods regularise this code to compose additively
arXiv:2609.23979v1 Announce Type: cross Abstract: Attention encoder-decoder (AED) Speech Foundation Models achieve strong ASR performance but can generate acoustically unsupported text when inputs con
arXiv:2509.22030v2 Announce Type: replace Abstract: This paper examines how outliers, often dismissed as noise in topic modeling, can act as weak signals of emerging topics in dynamic news corpora. Us
arXiv:2609.23587v1 Announce Type: new Abstract: Large reasoning models (LRMs) incur high inference costs, often mitigated by efficiency techniques like quantization and pruning. However, the impact of
arXiv:2609.22135v1 Announce Type: new Abstract: Omni-modal large language models integrate text, audio, and image signals into a shared residual stream, where concepts such as emotion can be linearly