Knowledge catalogue
arXiv:2610.07881v1 Announce Type: new Abstract: Social preferences can promote cooperation in multi-agent reinforcement learning, but existing approaches often require agents to observe the rewards of
arXiv:2610.08077v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after intera
arXiv:2610.07057v1 Announce Type: cross Abstract: We introduce sHAIL-Causal, the causal specialization of the Saturated Hierarchical Atomic Incremental Learning (sHAIL) paradigm: a sequential staircas
arXiv:2610.07810v1 Announce Type: new Abstract: Search filters help guests navigate vast catalogs in two-sided marketplaces like Airbnb, and recommending the right filters can meaningfully lift bookin
arXiv:2602.16863v3 Announce Type: replace-cross Abstract: The ability to manipulate tools significantly expands the set of tasks a robot can perform. Yet, tool manipulation represents a challenging cl
since many people are asking me about the new math results from OpenAI, here is my take. 1. It uses symbolic AI (Lean, etc) in addition to LLMs which is what i said for years we would need to do; this
The Information: Source: Nvidia considered a last-minute OpenRouter bid, telling its leadership it was prepared to make a generous offer, but OpenRouter didn't want to wait — This July, Nvidia caught
arXiv:2610.07204v1 Announce Type: cross Abstract: Recent AI alignment work often frames alignment as a pre-deployment optimization problem: collect human feedback, learn preferences or principles, fin
arXiv:2610.08322v1 Announce Type: new Abstract: Selective forecasting abstains on high-risk test windows under a retained-coverage budget. Existing gates such as TEM (Brusokas et al., 2025) score each
arXiv:2610.07726v1 Announce Type: new Abstract: Videofluoroscopic Swallowing Study (VFSS) is one of the gold standard for diagnosing swallowing disorders, providing dynamic X-ray imaging of the swallo
As the title suggests I'm currently trying to make a modal to identify which app is being used. The thing is I don't have labelled data and generating it is out of question since that is a lot of work
arXiv:2610.07925v1 Announce Type: new Abstract: Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos containing moments relevant to a given text query. Despite recent progress,
The real news here isn’t the result; it’s what we were not told. 1. AI once tried to be a science. Now we get stuff like the completely vague report from OpenAI below, and a lot of ignorant questions
this is typical of the cluelessness of people who literarily don’t understand the difference between a. a neural network solving a problem by itself and b. a neural network proposing an answer and hav
arXiv:2610.08230v1 Announce Type: new Abstract: As video capture moves to handheld and edge devices, motion blur from camera shake has become a pervasive degradation that lowers perceptual quality and
arXiv:2610.07823v1 Announce Type: new Abstract: The AI CUP 2025 Precise Analysis of Table Tennis Smart Racket Data Competition introduced smart table tennis rackets that collect extensive player swing
arXiv:2610.07503v1 Announce Type: cross Abstract: Two populations of graphs often have to be compared without any correspondence between their vertices, for instance when networks come from different
arXiv:2610.07311v1 Announce Type: new Abstract: Agentic memory allows LLM agents to reuse past experience, yet retrieved memories can also distort inference even when they are benign, correctly stored
arXiv:2610.04687v2 Announce Type: replace Abstract: Answering questions over imperfect tables requires handling errors that can affect the answer. We investigate two challenges for large language mode
arXiv:2610.06938v1 Announce Type: new Abstract: Medical image segmentation remains fragmented along two axes: segmentation paradigms and data dimensionality. Existing methods are typically developed s
arXiv:2610.08225v1 Announce Type: new Abstract: In this work, we introduce Crazyflow, an accurate, differentiable simulator built on JAX. By leveraging jit compilation via XLA, Crazyflow unifies physi
arXiv:2610.06962v1 Announce Type: cross Abstract: In many review workflows the verdict is the only thing retained. The passages behind it are not marked, because that annotation costs far more than re
arXiv:2610.07097v1 Announce Type: new Abstract: Experimental studies of generative AI in education mostly report average effects, yet field evidence shows that AI can narrow attainment gaps or widen t
arXiv:2610.08402v1 Announce Type: new Abstract: Multi-turn LLM agents often receive sparse task feedback across several interactions, while generating each response token by token. This creates two re
arXiv:2610.07705v1 Announce Type: cross Abstract: The growing use of unmanned aerial vehicles (UAVs) has increased the importance of image-based UAV detection. Learning-based detectors are trained on
yep, this, too, like a bunch of other similar tweets, is typical of the cluelessness of people who literarily don’t understand the difference between a. a neural network solving a problem by itself an
arXiv:2503.14858v5 Announce Type: replace Abstract: Scaling up self-supervised learning has driven breakthroughs in language and vision, yet comparable progress has remained elusive in reinforcement l
arXiv:2610.06508v1 Announce Type: new Abstract: Illuminant estimation is a fundamental problem in computational photography, as it enables the correction of color shifts induced by varying lighting co
arXiv:2610.04300v1 Announce Type: new Abstract: The semantic information of objects in remote sensing images is typically invariant to geometric transformations from the dihedral group D4. However, SA
arXiv:2610.05058v1 Announce Type: cross Abstract: Pointwise Mutual Information (PMI) is a core measure of testing word association, and Skip-gram with Negative Sampling (SGNS) is essentially a method
arXiv:2610.04052v1 Announce Type: new Abstract: Shape from shading using a single image of a Lam- bertian surface is inherently ambiguous. When the light source direction is known, the surface normal
arXiv:2610.04285v1 Announce Type: cross Abstract: We develop an amortized, grid-free implementation of continuous Langevin dynamics based policy-value iteration for entropy-regularized, infinite-horiz
Artificial intelligence development firm Anaconda Inc. is enhancing its enterprise AI platform with tools to coordinate groups of AI agents, test their security and move applications into production.
Reuters: Anthropic says it found 5,500 verified vulnerabilities in April-October and Glasswing partners found 129K+ in April-July; 33K+ were critical or high severity — Anthropic is expanding a progra
arXiv:2610.04058v1 Announce Type: cross Abstract: In this paper we use machine learning methods to predict radiation damage in the lead tungstate crystals of the CMS electromagnetic calorimeter at the
arXiv:2610.06232v1 Announce Type: cross Abstract: Self driving vehicles have emerged as a reliable technology that has the capability to transform transportation and mobility. The development of self
arXiv:2610.04624v1 Announce Type: new Abstract: Recovering Partial Differential Equation (PDE) coefficient fields from extremely sparse observations is a severely ill-posed inverse problem for which g
Banger paper from Meta AI on research agents that decide what to investigate next. (bookmark it) If you run long-horizon research agents, choosing the next investigation is hard to learn, because thos
arXiv:2610.05674v1 Announce Type: cross Abstract: In GPS-denied or cluttered urban environments, vision-based landing is essential for reliable UAV missions. Real-world landing sites are often unstruc
arXiv:2610.03720v1 Announce Type: cross Abstract: Continuous colormaps are widely used to visualize scalar fields, and their quality is typically evaluated using measures such as discriminative power
arXiv:2610.05765v1 Announce Type: new Abstract: Goal-conditioned imitation learning (GCIL) with flow matching is a promising framework that can represent multimodal behaviors while adapting to diverse
arXiv:2610.04931v1 Announce Type: new Abstract: This paper introduces a real-time thumbnail optimization system deployed at a global O(B) scale on a major short-form video platform. Unlike traditional
arXiv:2610.04878v1 Announce Type: cross Abstract: Human-agent evaluations often compress interaction into a single performance score, even when human and automated policies adapt differently over time
arXiv:2103.16559v3 Announce Type: cross Abstract: Most successful self-supervised learning methods are trained to align the representations of two independent views from the data. State-of-the-art met
arXiv:2610.04357v1 Announce Type: new Abstract: We give checkable positive-definiteness criteria for the limiting neural tangent kernel (NTK) and high-probability finite-width gradient-descent guarant
arXiv:2610.04020v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) began as an unsupervised tool for decomposing neural representations into sparse, interpretable features, and are increasingl
arXiv:2610.05898v1 Announce Type: new Abstract: Real-world users often exhibit highly heterogeneous preferences over multiple objectives for LLM responses. A lightweight aligner can tailor these respo
arXiv:2603.11048v2 Announce Type: replace Abstract: We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting from charact
arXiv:2610.06104v1 Announce Type: new Abstract: Multimodal imitation learning requires diverse executable futures under the same observation and consistent behavior across replanning cycles. We presen
arXiv:2610.04605v1 Announce Type: new Abstract: Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues to semantically meaningful conce
Context compression is a huge bottleneck for long-running agents. This work finds that context compression hurts long-horizon agents at a few specific points. They propose PAIR, which replays the agen
In CUDA 13.1 “green contexts” let applications explicitly partition a GPU’s execution resources—such as Streaming Multiprocessors (SMs) and work‑queue slots—within one process. By assigning dedicated
arXiv:2610.04559v1 Announce Type: new Abstract: External causal reports can improve structure learning from limited observations, but their reliability varies across sources and variable pairs. We int
arXiv:2512.21029v2 Announce Type: replace-cross Abstract: We study the critical points over an algebraic variety of an optimization problem defined by a quadratic objective that is degenerate. This sc
arXiv:2610.04783v1 Announce Type: new Abstract: Counterfactual explanations are most useful when they can be generated with low latency, remain close to the factual input, and satisfy input-domain, ca
arXiv:2610.05678v1 Announce Type: new Abstract: Most humanoid loco-manipulation controllers require human motion data to learn whole-body coordination and posture, leaving policies reliant on external
arXiv:2610.06823v1 Announce Type: new Abstract: Large longitudinal cohorts often contain wrist accelerometry without optical heart-rate sensing, motivating recovery of cardiac information from motion
arXiv:2610.06331v1 Announce Type: new Abstract: Human demonstrations offer rich examples of precise dexterous manipulation and a promising source of robot training data. However, high-fidelity reprodu
arXiv:2610.04526v1 Announce Type: cross Abstract: Disasters can overload cellular control-plane signaling within minutes, yet fine-grained Radio Resource Control (RRC) or Next Generation (NG) Applicat
arXiv:2505.19058v2 Announce Type: replace Abstract: We propose a novel distributionally robust Q-learning algorithm for the non-tabular case accounting for continuous state spaces where the state tran