Knowledge catalogue
arXiv:2610.14671v1 Announce Type: new Abstract: Streaming video understanding requires answering questions from the observed video, with evidence drawn from recent observations or earlier events. Hist
arXiv:2610.14400v1 Announce Type: new Abstract: Successor-feature-based zero-shot reinforcement learning methods pre-train a task encoder and successor-feature predictor on offline, reward-free data,
arXiv:2610.15039v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models combine specialized experts through an input-dependent routing mechanism, and their sparse variants underpin many modern
SPCX isn't just building compute faster than every other neocloud It has something none of them have: OPTIONALITY on every GPU it deploys Every GW SpaceX brings online has two paths to revenue: 1. use
arXiv:2610.17904v1 Announce Type: new Abstract: Continual learning (CL) adapts pretrained models to a sequence of tasks while retaining knowledge acquired from earlier tasks. When task data are sensit
arXiv:2610.17483v1 Announce Type: new Abstract: Machine learning surrogates of partial differential equations (PDEs) are commonly trained on data generated by numerical solvers. Therefore, the trainin
arXiv:2610.14440v1 Announce Type: new Abstract: Asynchronous reinforcement-learning post-training of large language models is computationally efficient but inherently off-policy: the learner updates o
arXiv:2610.16828v1 Announce Type: new Abstract: When does a shared representation become insufficient for jointly supporting multiple tasks? This question lies at the heart of multi-task learning mode
arXiv:2610.16749v1 Announce Type: new Abstract: Recent foundation models have drastically improved the generalization of monocular relative depth estimation, yet recovering accurate metric depth from
arXiv:2610.17283v1 Announce Type: new Abstract: The success of autoregressive language models trained with Chain-of-Thought~(CoT) supervision raises a fundamental question: How simple can a next-token
arXiv:2508.04451v2 Announce Type: replace Abstract: Red teaming is essential for securing Large Language Models, yet current automated methods remain limited by templates and single-turn attacks. To s
arXiv:2610.14265v1 Announce Type: new Abstract: Recent advances in multi-modal large language models have shifted toward the 'thinking with images' paradigm to improve reasoning faithfulness, yet exis
arXiv:2610.16762v1 Announce Type: new Abstract: Keypoint detection plays a central role in geometric vision pipelines. Existing detectors exhibit complementary strengths across different scene structu
arXiv:2602.01581v2 Announce Type: replace Abstract: Aligning large language models (LLMs) depends on high-quality datasets of human preference labels, which are costly to collect. Although active lear
arXiv:2610.17999v1 Announce Type: new Abstract: Humanoid behavior foundation models (BFMs) enable diverse whole-body control, but adapting a pretrained controller to a new embodiment remains challengi
arXiv:2610.15365v1 Announce Type: cross Abstract: Large language models (LLMs) can produce harmful content while generating a response. A useful safeguard should not only detect this risk during gener
I've seen this one floating around quite a bit now and since this is something that can be done without the parent and or other dependencies i thought i'd share something. Usually when you fine-tune a
arXiv:2603.01498v3 Announce Type: replace Abstract: In remote sensing imagery, multi-class change detection (MCD) is crucial for fine-grained monitoring, yet it has long been plagued by feature ambigu
arXiv:2610.18552v1 Announce Type: cross Abstract: Teacher-free one-step generative models such as W-Flow learn directly from distributional objectives, with the Sinkhorn divergence providing the stron
arXiv:2610.17996v1 Announce Type: new Abstract: Sugarcane leaf diseases severely impact crop yield and quality, making accurate and timely detection critical for sustainable agriculture. Conventional
arXiv:2610.17019v1 Announce Type: cross Abstract: Whisper-style ASR models provide strong zero-shot transcription, but their residual errors are not evenly distributed across datasets, recording condi
arXiv:2610.15357v1 Announce Type: new Abstract: Generating complete 3D assets from sparse, unposed images requires preserving observed geometry while completing unseen regions. Joint reconstruction an
What's Changed mlx: port the Metal custom kernels to CUDA by @dhiltgen in #18657 docs: model recs and language standardization by @anra8571 in #18981 openai: accept custom tool calls in Responses hist
arXiv:2610.18189v1 Announce Type: new Abstract: Modern text-to-video (T2V) models generate visually compelling videos, yet meaning-preserving changes in prompt wording can substantially alter semantic
arXiv:2610.15354v1 Announce Type: new Abstract: Sexual harassment represents a pervasive societal challenge, with a substantial proportion of incidents remaining unreported due to insufficient evidenc
arXiv:2610.14517v1 Announce Type: new Abstract: During a network forward call, diffusion backbones naturally produce many intermediate activations. If we evaluate each activation against an identical
arXiv:2610.15850v1 Announce Type: new Abstract: Sparse autoencoder (SAE) features are typically discovered from how their activations co-vary with behaviour, yet they are often used through interventi
arXiv:2610.15689v1 Announce Type: cross Abstract: Flow matching can learn structure directly from data, raising the question of when additional constraints improve generation. We study penalties that
arXiv:2610.14009v1 Announce Type: new Abstract: Large AI models increasingly rely on distributed GPU execution, yet it remains unclear whether established failure analysis methods transfer effectively
arXiv:2610.18846v1 Announce Type: new Abstract: Reconstructing complete, high-quality meshes of large-scale scenes from unposed multi-view images requires faithful geometric grounding while plausibly
For three years, artificial intelligence infrastructure has been dominated by one idea: Bigger is better. Bigger models, bigger clusters, and bigger checks written to a small group of suppliers. At th
AWS engineers share kernel optimizations for fused Mixture-of-Experts (MoE) models on Amazon SageMaker AI: Swap-AB for WGMMA utilization, Triton backend routing for FP8 quantization, and eliminating T
We trained a model on agentic coding tasks using fully asynchronous RL and mixed-precision, mixed-accelerator samplers. With off-policy correction, training stayed stable through convergence, on par w
arXiv:2610.13744v1 Announce Type: new Abstract: On-policy self-distillation promises to replace the sparse outcome signal of verifiable-reward RL with dense token-level credit: a teacher conditioned o
arXiv:2610.12972v1 Announce Type: new Abstract: Humanoid robots performing lifting and material-handling tasks must maintain balance despite unknown and varying payloads. However, payload uncertainty
arXiv:2610.13273v1 Announce Type: cross Abstract: API specifications serve as critical documentation for modern software development, directly impacting integration efficiency and client code generati
The no-cache path builds a [n_tokens, n_tokens] mask and passes K and V unpadded, so FLASH_ATTN_EXT sees K->ne[1] == n_tokens. The CUDA kernels for head size 512 require a multiple of FATTN_KQ_STRIDE,
arXiv:2610.12997v1 Announce Type: new Abstract: Prior-art retrieval systems are structurally organized around classification codes, making cross-code discovery difficult. This paper asks if an unsuper
arXiv:2610.12598v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary
arXiv:2610.13277v1 Announce Type: cross Abstract: Memory-augmented assistants retrieve evidence from stored conversations and documents to answer queries. Most embedding-based retrievers compare singl
arXiv:2603.00530v2 Announce Type: replace Abstract: Sampling from unnormalized densities using diffusion models has emerged as a powerful paradigm. However, while recent approaches that use least-squa
arXiv:2610.13693v1 Announce Type: cross Abstract: Neural networks (NNs), while highly flexible and versatile, are often poorly calibrated. Post-hoc calibration methods adjust the outputs of an already
arXiv:2610.12567v1 Announce Type: new Abstract: Prior research on learning from humans often requires real human demonstrations. But advances in video generation models offer a new paradigm: we can no
arXiv:2610.12872v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong individual task performance, yet still struggle to collaborate with users over extended, multi-turn inte
arXiv:2410.06786v2 Announce Type: replace Abstract: In this study, we present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data. Our approach draws inspi
arXiv:2610.13649v1 Announce Type: cross Abstract: Machine learning methods are increasingly used to predict chemical properties directly from the molecular structure to bypass the often prohibitive co
arXiv:2610.13508v1 Announce Type: new Abstract: Federated learning (FL) seeks to optimize a shared global model from decentralized client data. While effective for average performance, this process ca
arXiv:2610.13267v1 Announce Type: new Abstract: Large language model (LLM) agents are highly vulnerable to memory-poisoning attacks. Existing defenses primarily rely on external modules for either sta
arXiv:2610.13321v1 Announce Type: new Abstract: Web crawling is a major source of large language model (LLM) pretraining data, yet data-selection pipelines discard a large share of crawled pages. We i
arXiv:2610.13764v1 Announce Type: cross Abstract: Prior-data fitted networks (PFNs) are trained to approximate the Bayesian posterior predictive distribution (PPD) of a synthetic prior, yet results ab
arXiv:2610.12738v1 Announce Type: cross Abstract: Forecasting rare, high-cost events in multivariate time-series systems is hard because their precursors are seldom observed, so a purely data-driven m
arXiv:2610.12657v1 Announce Type: cross Abstract: Efficient autoregressive generation is increasingly limited by the memory footprint of the key-value (KV) cache, which grows linearly with sequence le
arXiv:2610.13060v1 Announce Type: new Abstract: KV-cache reuse in large language model serving is commonly limited to exact prompt prefixes, preventing reuse when the same retrieved document appears a
arXiv:2610.13732v1 Announce Type: cross Abstract: Scaling generalist robotic policies is limited by the high cost of collecting embodied interaction data. Large-scale egocentric human videos offer a r
Paper: Looped Diffusion Transformer (arXiv 2609.40305, 30 Sep). Instead of making a text-to-image DiT bigger, it runs a shared group of transformer blocks several times inside each denoising step. The
arXiv:2610.13755v1 Announce Type: cross Abstract: Training long-horizon language model agents requires assigning credit to intermediate decisions from sparse terminal feedback. Within a finite group o
arXiv:2610.12794v1 Announce Type: cross Abstract: Large Language Model (LLM)-guided evolutionary optimization has successfully improved prompts, programs, and even entire AI systems. Most optimization
arXiv:2610.13943v1 Announce Type: new Abstract: Pretrained vision-language-action (VLA) models encode broad manipulation priors, yet adapting them to specific tasks requires balancing limited robot in
arXiv:2610.13826v1 Announce Type: cross Abstract: Recent advances in automatic pronunciation assessment (APA) have driven a shift from scripted to free-form assessment. However, existing methods often
arXiv:2610.13334v1 Announce Type: new Abstract: Motivated by the success of large language models (LLMs) with broad generalizability and robustness to noisy or unreliable pre-training data, we explore