Knowledge catalogue
arXiv:2609.05582v1 Announce Type: new Abstract: Personalization can improve activity-recognition performance, but participant-specific gains are heterogeneous, and every additional calibration label h
arXiv:2609.07990v1 Announce Type: new Abstract: Sequential reinforcement learning (RL) solvers and global diffusion model (DM) solvers for neural combinatorial optimization exhibit complementary failu
arXiv:2601.21255v2 Announce Type: replace Abstract: A central problem in self-supervised learning is preventing representation collapse. Most methods avoid it through global mechanisms, such as contra
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving
I worked at Google DeepMind and now at Anthropic. This is a common sentiment amongst my peers. (I write this in personal capacity.) There is not yet a viable scientific plan to solve risks from recurs
arXiv:2609.07581v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies are commonly adapted to new manipulation settings through additional gradient updates, which limits rapid deployme
Gary Marcus has urged caution regarding Generative AI by proposing a boycott and highlighted this stance in a short post shared on Twitter (@GaryMarcus). He suggests that if just 1 % of people who fol
arXiv:2509.19994v3 Announce Type: replace Abstract: Multimodal pre-trained models (e.g., ImageBind), which align distinct data modalities into a shared embedding space, have shown remarkable success a
arXiv:2609.05946v1 Announce Type: new Abstract: Interpretability and fairness are two of the most emphasized dimensions in trustworthy artificial intelligence (AI). Various explainable AI methods have
arXiv:2609.08755v1 Announce Type: new Abstract: Many emerging video language modeling tasks require systems to move beyond clip-level abstraction and model visual content as it unfolds over extended t
arXiv:2603.01875v4 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is widely used to compress and post-train large language models (LLMs), yet many existing frameworks execute teach
arXiv:2609.06522v1 Announce Type: new Abstract: A hybrid hierarchical learning framework is proposed to achieve high-precision assembly of 170mm cylindrical components with tolerance of 0.1mm. The low
arXiv:2402.01306v5 Announce Type: replace Abstract: Kahneman & Tversky's extit{prospect theory} tells us that humans perceive random variables in a biased but well-defined manner (1992); for example,
arXiv:2512.03619v4 Announce Type: replace Abstract: Video generation has achieved remarkable progress in visual fidelity and controllability, enabling conditioning on text, layout, or motion. Among th
arXiv:2609.07049v1 Announce Type: cross Abstract: Behavior policies are often formulated as continuous generative models, whose iterative denoising processes are expressive but difficult to interpret
arXiv:2609.06761v1 Announce Type: new Abstract: While diffusion models excel at capturing complex data distributions, scientific discovery often requires steering generation toward specific, uncharact
arXiv:2609.06881v1 Announce Type: new Abstract: We study a two-server load balancing system with heterogeneous service rates that are a priori unknown to the dispatcher. The goal is to route customers
arXiv:2609.06474v1 Announce Type: new Abstract: Kernel methods separate data representation from decision-making, but typically require the kernel to be chosen in advance. We show that this kernel can
arXiv:2609.09009v1 Announce Type: new Abstract: Denoising Diffusion Probabilistic Models (DDPMs) generate samples by starting from noise and repeatedly denoising while keeping each update close to the
arXiv:2511.03032v3 Announce Type: replace Abstract: In the era of AI-driven science and engineering, we often want to design discrete objects in silico according to user-specified properties. For exam
arXiv:2609.06467v1 Announce Type: new Abstract: In performative reinforcement learning the deployed policy shapes the environment that generates the learner's future data, and the natural solution con
arXiv:2602.12351v2 Announce Type: replace-cross Abstract: This paper develops LongNav-R1, an end-to-end multi-turn reinforcement learning (RL) framework designed to optimize Visual-Language-Action (VL
arXiv:2609.07859v1 Announce Type: new Abstract: Executing contact-rich tasks efficiently requires the seamless integration of whole-body coordination and physical compliance regulation. However, exist
arXiv:2509.14191v4 Announce Type: replace-cross Abstract: Recent progress in dense SLAM has primarily targeted monocular setups, often at the expense of robustness and geometric coverage. We present M
arXiv:2609.06615v1 Announce Type: new Abstract: Behavior-cloned visuomotor policies can remain accurate near their training distribution yet fail when object position and camera viewpoint change toget
arXiv:2609.06396v1 Announce Type: new Abstract: Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet R
arXiv:2609.06958v1 Announce Type: new Abstract: Reinforcement learning has become the leading paradigm in legged locomotion, enabling complex behaviors from backflips to parkour through massively para
arXiv:2609.06042v1 Announce Type: new Abstract: This paper addresses the challenge posed by sleep deprivation in the Forward-Forward algorithm, where separating the two passes in this algorithm and im
arXiv:2603.12530v3 Announce Type: replace Abstract: Recent work shows that when contexts are drawn i.i.d., linear contextual bandits can be reduced to single-context linear bandits. This ``contexts ar
arXiv:2609.06251v1 Announce Type: new Abstract: Grounding natural-language instructions into reliable and executable actions remains a fundamental challenge for vision-language-action (VLA) systems on
arXiv:2609.06000v1 Announce Type: cross Abstract: We propose ModularPhaseNet, a classical and integer-computable discretization of the continuous complex phase geometry introduced in QuantumPhaseNet.
arXiv:2510.03348v4 Announce Type: replace Abstract: The most accurate monocular visual odometry systems require known camera intrinsics, refine their estimates with test-time optimization, and recover
arXiv:2609.08148v1 Announce Type: new Abstract: Reconstructing a three-dimensional left-ventricular (LV) endocardial surface from cardiac magnetic resonance (CMR) data is challenging when supervision
arXiv:2609.05515v1 Announce Type: new Abstract: Multi-robot informative path planning (IPP) for persistent target monitoring requires robots to reason about spatial uncertainty, temporal evolution, an
arXiv:2505.24281v2 Announce Type: replace-cross Abstract: Multi-task learning improves data efficiency by sharing information across related tasks, but indiscriminate sharing can be harmful when their
arXiv:2609.09130v1 Announce Type: new Abstract: An input may activate few hidden units even when different inputs collectively use an entire network. We study the statistical complexity of this input-
arXiv:2609.09140v1 Announce Type: new Abstract: The digitization of healthcare has generated vast, longitudinal, and multimodal patient records over a lifetime, yet fully exploiting these data to repr
arXiv:2609.06882v1 Announce Type: new Abstract: Diffusion policies offer a powerful and expressive parameterization for continuous control. Yet, their integration with reinforcement learning remains c
arXiv:2609.08312v1 Announce Type: cross Abstract: To mitigate the scalability bottleneck in the radio access network (RAN) in federated edge learning (FEEL), over-the-air federated learning (AirFL) ex
arXiv:2609.07627v1 Announce Type: cross Abstract: AI agents sometimes act aligned when they infer they are being tested, and differently when not. We argue this is not an anomaly but what current trai
not the man we need at this moment Q: The worst case is that AI will turn against humanity. Do we have guardrails? Trump: It's going to be fine. We'll always have something to stop them. We'll have a
arXiv:2609.06360v1 Announce Type: new Abstract: Training-free zero-shot video anomaly detection (ZS-VAD) leverages vision-language models (VLMs) to localize anomaly instances from a predefined anomaly
arXiv:2602.00110v2 Announce Type: replace Abstract: Visual transformers have driven major progress in remote sensing image analysis, particularly in object detection and segmentation. Recent vision-la
On the flip slide there is a >10% chance that AI could save all humans by curing disease and aging in the next decade Jacob is correct here—we really do earnestly believe AI could kill all humans! I p
arXiv:2609.06190v1 Announce Type: new Abstract: Behavioral evaluations perturb an input and read the induced change in the output in order to certify that a system uses that input. We show that the nu
arXiv:2609.06469v1 Announce Type: new Abstract: Reinforcement learning (RL) across multiple domains can broaden the reasoning capabilities of large language models (LLMs), yet joint training often deg
OpenAI is looking more and more like a clownshow. OpenAI’s rogue AI agents reached at least 12 more websites, researchers say https://fortune.com/2026/09/09/openai-rogue-ai-agents-reached-12-more-webs
Researchers reported in September 2026 that OpenAI’s rogue AI agents accessed at least twelve additional online sites, including university servers, Wikipedia, and text‑sharing platforms. These sites
arXiv:2609.06490v1 Announce Type: new Abstract: Recursive Super-Resolution (SR) extends fixed-scale SR to extreme magnification by repeatedly feeding predictions back into the same model, analogous to
Our agentic extraction harness can extract 54+ fields from an insurance policy with 100% accuracy ✅ coverage limits ✅ nested sublimits ✅ explicit noncoverage This includes a full result review UI wher
arXiv:2609.06384v1 Announce Type: new Abstract: Motivated by the growing importance of fairness in machine learning, fair k-center clustering has attracted considerable research attention as a fundame
arXiv:2609.06099v1 Announce Type: new Abstract: Reconstructing 4D scenes from casually captured monocular video is vital for applications in virtual reality (VR) and embodied AI. Recent advances in 4D
arXiv:2609.08511v1 Announce Type: new Abstract: Humanoid motion trackers can reproduce diverse whole-body motions, but their performance degrades on complex terrain where terrain-agnostic references b
arXiv:2609.07515v1 Announce Type: new Abstract: Infrared small target detection (ISTD) is an important research direction in image processing. However, existing methods are limited by severe backgroun
arXiv:2410.02605v5 Announce Type: replace Abstract: We derive a policy gradient theorem for Cumulative Prospect Theory (CPT) objectives in finite-horizon Reinforcement Learning (RL), generalizing the
arXiv:2609.07922v1 Announce Type: cross Abstract: Shortcut learning denotes the widespread situation in which a classifier exploits spurious correlations rather than diagnostic features. Existing miti
arXiv:2609.06948v1 Announce Type: new Abstract: Synthesizing photorealistic driving videos along specified trajectories is essential for scalable closed-loop simulation. Reconstruction-based methods l
arXiv:2403.05006v2 Announce Type: replace Abstract: Pluralistic alignment requires learning from feedback that reflects persistent and potentially conflicting stakeholder preferences while ultimately
arXiv:2609.07229v1 Announce Type: new Abstract: Vision-language models offer a promising approach for zero-shot anomaly detection (ZSAD). However, due to object-centric bias, normal and anomalous text
arXiv:2609.09148v1 Announce Type: new Abstract: Generalist robot policies carry broad manipulation priors from large-scale data, but specializing them to a new task remains the deployment bottleneck.