Knowledge catalogue
arXiv:2610.06627v1 Announce Type: cross Abstract: The information bottleneck (IB) seeks a representation U of a source X that retains as much information as possible about a target Y, subject to a con
arXiv:2610.06096v1 Announce Type: new Abstract: In self-supervised learning, a third modality should improve, or at least preserve, performance. Across nine image-text-tabular datasets, we show that i
arXiv:2610.04424v1 Announce Type: new Abstract: To mitigate the quadratic complexity bottleneck of the Transformer, sparse attention has emerged as a pivotal technology. Despite the extensive empirica
arXiv:2610.03829v1 Announce Type: cross Abstract: Real-world outpatient oncology notes contain specialised terminology, tumour staging expressions, treatment names, toxicity descriptions, and institut
arXiv:2610.04155v1 Announce Type: cross Abstract: Open electromagnetic-transient datasets are beginning to make reproducible learning-based protection studies possible, but the practical use of these
arXiv:2610.06852v1 Announce Type: new Abstract: Pipeline figures in ML papers must be repurposed across many canvases, including paper columns, 16:9 slides, portrait posters, 1:1 social teasers, 9:16
arXiv:2610.03952v1 Announce Type: new Abstract: A one-step curvature probe evaluates an initial direction, whereas continual learners are judged after reaching comparable new-task fit. In an overparam
arXiv:2610.04454v1 Announce Type: new Abstract: Recently, Drifting Models and Wasserstein Gradient Flows have attracted substantial attention because they move iterative distributional refinement to t
One thing I'd LOVE to understand is how Claude 'knows' what the music from Secret of Monkey Island sounds like Maybe Anthropic crawled a whole bunch of online music discussion forums with text-based r
arXiv:2610.04853v1 Announce Type: new Abstract: In weakly supervised Whole Slide Image (WSI) classification, feature extractors typically compress each image tile into a single global embedding. Conse
arXiv:2610.04967v1 Announce Type: new Abstract: Prompting guides language model behavior through the initial context, whereas activation steering often intervenes throughout generation. A natural ques
arXiv:2610.05810v1 Announce Type: cross Abstract: Machine learning (ML)-powered poisoning attack vectors are adversarial maneuvers whereby an attacker intentionally inserts, corrupts, or alters traini
arXiv:2607.13029v2 Announce Type: cross Abstract: We study online control of a known linear dynamical system with adversarial costs and bounded disturbances, measuring regret against a general class o
arXiv:2408.00310v2 Announce Type: replace Abstract: We study Online Linear Programming (OLP) with batching. The planning horizon is cut into K batches, and decisions on orders can be delayed to the en
arXiv:2610.04552v1 Announce Type: new Abstract: Fusing radar, LiDAR, and camera enables robust perception in diverse and adverse conditions, but the fusion performance critically depends on accurate e
arXiv:2610.04572v1 Announce Type: new Abstract: Precise constraint satisfaction is a prerequisite to deploying learned models in many areas, motivating methods that repair raw neural predictions with
arXiv:2610.06360v1 Announce Type: cross Abstract: Reinforcement learning post-training for language models relies on two reward designs: human preferences (RLHF, DPO) and binary verifiers (RLVR). Clin
arXiv:2412.12740v2 Announce Type: replace Abstract: Robots need to be able to understand their surroundings in order to operate safely and robustly, and to interact with the surrounding environment. R
OpenAI: OpenAI releases a range of new mathematical results produced by an internal model, with details like estimations of compute spent in terms of ChatGPT Pro usage — We're releasing a broad range
Joseph Howlett / Scientific American: OpenAI says its internal model produced 372 math results, nearly all from a single prompt handed to a single AI agent; some might have taken multiple attempts — A
OpenAI will automatically apply a proprietary “textGrain” watermark to ChatGPT‑generated text within the European Union as required by the EU AI Act, while enabling the feature elsewhere but keeping i
arXiv:2610.05017v1 Announce Type: new Abstract: Concept-based methods provide a semantic level for interpreting and manipulating learned representations, but existing editing approaches are typically
arXiv:2610.05359v1 Announce Type: new Abstract: Model Predictive Control (MPC) provides a structured and constraint-aware mechanism for decision-making, but its reliance on optimization-friendly analy
arXiv:2610.05038v1 Announce Type: cross Abstract: We present an oracle-optimal method for finite-sum monotone inclusions under mean-square Lipschitz continuity. Our switching regularization method fin
arXiv:2610.04249v1 Announce Type: new Abstract: Recent successes of matrix- and curvature-based optimizers have renewed interest in how update geometry shapes learning. These methods normalize or prec
arXiv:2503.19945v4 Announce Type: replace-cross Abstract: Mammography, an X-ray-based imaging technique, remains central to the early detection of breast cancer. Recent advances in artificial intellig
arXiv:2610.06116v1 Announce Type: new Abstract: Modern LLM optimizers such as Muon often produce weight matrices with higher effective rank than Adam, yet further spectral control has delivered only m
arXiv:2610.04937v1 Announce Type: cross Abstract: Level-K reasoning generates a hierarchy of policies specialized to opponents with different reasoning levels. When an opponent's level is unknown, a c
arXiv:2610.05191v1 Announce Type: new Abstract: DETR-style detectors use one-to-one bipartite matching during training to assign object queries to ground-truth objects, enabling end-to-end set predict
arXiv:2504.09663v3 Announce Type: replace Abstract: I show that ordinary least squares (OLS) predictions can be rewritten as the output of a restricted attention module, akin to those forming the back
arXiv:2610.04602v1 Announce Type: new Abstract: Primitive-based 3D segmentation offers a compact and explicit alternative to dense surface prediction, naturally supporting structural abstraction and b
arXiv:2610.06709v1 Announce Type: cross Abstract: Learning the Hamiltonian of a many-body system from its dynamics is a central task in quantum science, yet the algorithms with the strongest provable
arXiv:2610.05070v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) provides denser token-level supervision and better computational efficiency than Reinforcement Learning with Verifiab
arXiv:2610.06686v1 Announce Type: new Abstract: Long context inference with large language models becomes increasingly expensive as attention must operate over an ever growing KV cache. Page sparse at
With llama.cpp using a customized SYCL backend on Intel B70 (32GB), overclocking my DDR5 memory gave modest gains for MoE models which do not fit in VRAM. Both PP and TG increased after overclocking D
arXiv:2610.06002v1 Announce Type: cross Abstract: Diffusion models provide expressive priors over trajectories, but adapting these priors to test-time constraints requires maintaining feasibility and
arXiv:2610.05732v1 Announce Type: new Abstract: LLM agents rely on long-term memory to retain and reuse information when performing tasks over long horizons. Existing methods provide limited support f
arXiv:2610.04226v1 Announce Type: new Abstract: LoRA-based continual learning methods mitigate catastrophic forgetting through various mechanisms, yet nearly all complement these with small learning r
Looped language models repeatedly apply a weight-shared block to increase effective depth without increasing parameter count, but the resulting T sequential recurrent-block calls per generated token s
arXiv:2610.06817v1 Announce Type: cross Abstract: We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them. Paradee
arXiv:2610.06230v1 Announce Type: new Abstract: A multi-domain eXtended Physics-Informed Neural Network (XPINN) framework is developed for nonsmooth Delay Differential Equations (DDEs). This is the fi
arXiv:2610.04089v1 Announce Type: new Abstract: Coding agents operating under ambiguous instructions or user prompts must decide whether to ask clarifying questions or attempt a solution directly. Whi
arXiv:2610.04652v1 Announce Type: new Abstract: Transferable adversarial attacks are arguably the most practical black-box threat model. Under the same perturbation budget, stronger transfer attacks a
arXiv:2610.06020v1 Announce Type: new Abstract: Volume electron microscopy (vEM) has emerged as an essential sensing technique in biomedical research, allowing the three-dimensional imaging of biologi
arXiv:2610.04657v1 Announce Type: new Abstract: Directed graphs naturally model many real-world systems in which interactions are asymmetric, such as citation networks, web graphs, and information-flo
arXiv:2610.04765v1 Announce Type: new Abstract: In this paper, we develop a method that enables bimanual dexterous hands to manipulate articulated objects with a high success rate without suffering fr
arXiv:2610.06062v1 Announce Type: new Abstract: Federated multi-player multi-armed bandit problems model collaborative sequential decision-making where multiple players interact with a common bandit e
arXiv:2610.05122v1 Announce Type: new Abstract: In recent years, Unmanned Aerial Vehicles (UAVs) or drones have been increasingly adopted in urban environments for applications such as parcel delivery
arXiv:2610.05115v1 Announce Type: new Abstract: Small targets occupy few patches in a vision-language encoder, so spatial features often mix object appearance with surrounding content. We propose Prot
arXiv:2603.13663v2 Announce Type: replace Abstract: The success of vision transformers-especially for generative modeling-is limited by the quadratic cost and weak spatial inductive bias of self-atten
arXiv:2503.09368v2 Announce Type: replace Abstract: Despite recent progress in learned image compression, current image codecs still struggle to maintain realistic reconstructions at low bit-rates, of
arXiv:2610.04047v1 Announce Type: cross Abstract: A language model reads long text in one quadratic forward pass, stops at the context window, and loses accuracy with length before reaching it. We ask
arXiv:2610.04659v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies commonly learn action chunks through a fixed left-to-right (LTR) factorization, although the same expert traject
arXiv:1908.04284v5 Announce Type: replace-cross Abstract: In this paper, we propose 'personal VAD', a system to detect the voice activity of a target speaker at the frame level. This system is useful
arXiv:2610.04616v1 Announce Type: cross Abstract: A vision--language--action (VLA) policy can complete complex tasks while ignoring the evidence that should determine its actions. An object held near
arXiv:2610.04997v1 Announce Type: new Abstract: We study offline learning in two-player zero-sum contextual games with public and private information, motivated by strategic settings such as auctions
arXiv:2610.04537v1 Announce Type: new Abstract: On-device assistants run GPU-based LLM inference alongside CPU retrieval on unified-memory systems. Under a saturated local-retrieval workload, four con
arXiv:2610.05844v1 Announce Type: cross Abstract: Recovering complete phase sets from powder X-ray diffraction (PXRD) is challenging when weak-phase peaks overlap stronger signals. A natural strategy
arXiv:2610.05004v1 Announce Type: new Abstract: Full-wave electromagnetic (EM) simulation enables accurate patch-antenna analysis but is computationally expensive for large-scale forward prediction an
arXiv:2607.15527v2 Announce Type: replace Abstract: Physical simulations that predict the behavior of urban disasters, such as climate-related flooding, play a crucial role in disaster prevention and