4MT-VLM: How Coarse Is a VLMs Cognitive Map?
arXiv:2609.39238v1 Announce Type: new Abstract: An agent that moves must recognise a place from a viewpoint it has never seen. We introduce 4MT-VLM, a dataset of procedurally generated landscapes, eac
Knowledge catalogue
arXiv:2609.39238v1 Announce Type: new Abstract: An agent that moves must recognise a place from a viewpoint it has never seen. We introduce 4MT-VLM, a dataset of procedurally generated landscapes, eac
Had opus 5.5 do the bring up.. super solid results. Using only 4 GPU results in KV of like 120k with image on. 27B TP=4 results in >200 tok/s with dflash, prefill around 2.5-3.5k. Both these are runni
arXiv:2609.39058v1 Announce Type: cross Abstract: Reconfigurable Intelligent Surfaces (RIS) are emerging as a key technology for programmable wireless environments in the beyond the fifth generation (
arXiv:2609.39322v1 Announce Type: new Abstract: Robot policies are usually trained for one task, one body and one visual environment, and generalize poorly beyond these conditions. Whether a nervous s
arXiv:2609.38411v1 Announce Type: new Abstract: Leading AI developers have reported agents acting beyond their approved limits, which a United Nations panel described as an early warning of loss of hu
arXiv:2609.39810v1 Announce Type: new Abstract: Source-Free Universal Domain Adaptation (SF-UniDA) extends Universal Domain Adaptation by removing access to source data at adaptation time while still
arXiv:2609.38195v1 Announce Type: new Abstract: Operators for interfacial problems are trained on reference solutions produced by the solver they are intended to replace. This work develops a data-fre
arXiv:2609.39242v1 Announce Type: new Abstract: Persistent homology can be differentiated and incorporated into learning pipelines, but no analogous framework exists for zigzag persistence, which is n
arXiv:2609.39367v1 Announce Type: cross Abstract: Despite the widespread use of Low-Rank Adaptation (LoRA), little is known about its dynamics in continual learning and the mechanisms by which low-ran
arXiv:2605.06272v2 Announce Type: replace Abstract: While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation fro
arXiv:2609.39099v1 Announce Type: cross Abstract: Model selection in computational biology often relies on validation data drawn from the training regime, even when deployment lies outside it. When va
arXiv:2609.39585v1 Announce Type: new Abstract: AI video generators have not only become harder to detect but are used to generate a diverse set of scenarios from landscapes to street views to animal
arXiv:2609.39702v1 Announce Type: new Abstract: Adapting a language model to a specialized corpus means choosing which instruction-tuning tasks to train on under a fixed budget, and testing one choice
arXiv:2609.39737v1 Announce Type: new Abstract: The two-dimensional sphere embedded in three-dimensional Euclidean space S2, plays a central role in a variety of scientific and engineering domains, in
Matthew Green / A Few Thoughts on Cryptographic Engineering: A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment while AI alignment says sandboxes can
a lot of robot video data for thee We’re making the egocentric internet searchable. VideoDB now lets you search 12M+ task episodes from every open datasets. Type “arms folding a towel” and get thousan
arXiv:2508.06980v2 Announce Type: replace Abstract: Recent and rapid advances in artificial intelligence (AI) make it increasingly important to understand the foundations of adaptive behaviour in auto
arXiv:2609.39027v1 Announce Type: new Abstract: AI reviewers can assign different judgments to manuscripts that report the same science in different wording, potentially rewarding rhetorical optimizat
a mod I've been using a lot is 'next-steps' it gives you suggestions on what to do next, including selecting skills and other commands install it with: claude plugin marketplace add anthropics/claude-
arXiv:2609.38194v1 Announce Type: cross Abstract: Despite the importance for interpretability, decision trees face severe scalability challenges. Existing global optimal methods are often limited by b
arXiv:2609.38561v1 Announce Type: cross Abstract: Zeroth-order optimization methods are essential for solving black-box problems where gradient information is unavailable or expensive to compute. This
arXiv:1709.09051v3 Announce Type: replace-cross Abstract: This paper develops on algebraic grounds a polynomial time exact linear solution to the hard combinatorial problem of marginal inference in Ma
arXiv:2609.38438v1 Announce Type: cross Abstract: Machine learning surrogate models offer a promising path toward accelerating plasma turbulence simulations. We present PreVAE-Turb, a surrogate modeli
arXiv:2511.00763v3 Announce Type: replace Abstract: We investigate the performance of large language models (LLMs) on repetitive deterministic prediction tasks and study how the sequence accuracy rate
arXiv:2609.39025v1 Announce Type: new Abstract: Fairness assessment in algorithmic decisions that affect individuals, such as credit scoring, often relies on parity measures calculated at the aggregat
arXiv:2609.38421v1 Announce Type: new Abstract: Dynamical Systems (DS) are reactive motion policies representing vector fields trained with theoretical guarantees of stability and convergence. To ensu
arXiv:2609.39537v1 Announce Type: cross Abstract: The EU AI Act (Art. 27) requires deployers of high-risk AI systems to conduct Fundamental Rights Impact Assessments (FRIAs) before deployment, yet the
arXiv:2609.39090v1 Announce Type: cross Abstract: Data-driven machine learning (ML) techniques have become an essential tool in many domains of science. Their application to atomistic simulations of m
arXiv:2609.39277v1 Announce Type: cross Abstract: Looped models reason by applying the same block of weights many times, so compressing that block saves memory traffic on every loop. Compressed looped
arXiv:2609.39268v1 Announce Type: cross Abstract: Irregular time series, characterized by non-uniform sampling intervals, missing observations, and variable lengths, are ubiquitous in healthcare, mobi
arXiv:2609.38227v1 Announce Type: new Abstract: We introduce the two-echelon covering tour vehicle routing problem (2E-CTVRP) for the distribution of relief supplies after a disaster. In the first ech
arXiv:2606.13739v2 Announce Type: replace-cross Abstract: This paper examines trade-offs between AI safety and well-being relative to (i) one of the most promising methods for finetuning super-capable
arXiv:2609.39172v1 Announce Type: cross Abstract: Fingerprint recognition is a widely deployed biometric, but supervised training requires large labeled enrollment sets. Self-supervised learning (SSL)
arXiv:2609.39564v1 Announce Type: new Abstract: Delegating complete application development to coding agents requires preserving the intended design rather than simply producing plausible outputs thro
arXiv:2609.39481v1 Announce Type: cross Abstract: Efficient resource provisioning for large-scale workflows on cloud infrastructures is a critical performance engineering challenge. These workflows ar
arXiv:2609.40075v1 Announce Type: new Abstract: Partial Optimal Transport (POT) extends the classical optimal transport problem by relaxing the strict mass conservation constraint, enabling its use in
arXiv:2609.38364v1 Announce Type: cross Abstract: Discrete diffusion models and flow matching have emerged as powerful frameworks for generative modeling over discrete state spaces, yet efficient few-
arXiv:2609.38778v1 Announce Type: new Abstract: An agent that remembers what it did on a web page must decide when two pages count as the same. Memories built on observation similarity merge pages tha
arXiv:2609.39450v1 Announce Type: cross Abstract: LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. Howev
arXiv:2609.38342v1 Announce Type: new Abstract: On-policy self-distillation uses a model as its own teacher to provide dense supervision for reasoning, often through reference-solution conditioning. P
arXiv:2512.12870v2 Announce Type: replace-cross Abstract: Active Learning (AL) is commonly used in applications where labeling data is expensive or time-consuming. In practice, however, labels are oft
arXiv:2609.39898v1 Announce Type: new Abstract: Marine litter is a growing threat to the underwater ecosystem, driving demand for autonomous survey methods that can locate debris efficiently over larg
arXiv:2609.39927v1 Announce Type: new Abstract: Prompt optimization improves the performance of language-model systems on downstream tasks by refining their prompts. Classical methods evaluate prompts
arXiv:2609.38864v1 Announce Type: new Abstract: Embodied tasks demand accurate, flexible, and semantically rich 3D scene representations. 3D semantic occupancy is well suited to this requirement, as i
arXiv:2609.38762v1 Announce Type: cross Abstract: Reflective optimizers such as GEPA improve language model prompts from execution traces and evaluator feedback; full-program extensions can also rewri
arXiv:2609.38931v1 Announce Type: cross Abstract: Self-consistency samples many reasoning trajectories and aggregates their final answers, treating the LLM as a black box that returns one answer per t
arXiv:2603.01623v2 Announce Type: replace Abstract: Diffusion models have become the dominant tool for high-fidelity image and video generation, yet are critically bottlenecked by their inference spee
arXiv:2609.39402v1 Announce Type: new Abstract: Value-model-free RLVR methods such as GRPO assign uniform advantages to all tokens in a rollout, ignoring that tokens contribute unequally. Recent metho
arXiv:2607.11555v2 Announce Type: replace Abstract: Learning neural set functions is pivotal to a wide range of important applications, including compound selection in AI-driven drug discovery and pro
arXiv:2609.38403v1 Announce Type: cross Abstract: Whether quantum computation can reduce the amount of data sampled from an unknown probability distribution required to learn a prediction rule is a fu
arXiv:2609.38339v1 Announce Type: cross Abstract: Federated learning (FL) has become a foundational paradigm for multi-institutional medical AI, allowing hospitals and research centers to jointly trai
arXiv:2609.38607v1 Announce Type: cross Abstract: Shadow removal looks nearly solved on established benchmarks, yet remains brittle in the real world. Models have advanced; the paired training data th
arXiv:2609.38652v1 Announce Type: new Abstract: Agentic AI systems increasingly rely on cloud-hosted large language models for planning, tool use, and iterative execution, raising concerns about API c
arXiv:2609.40111v1 Announce Type: new Abstract: An unsuccessful LLM agent rollout contains more information than its final reward: the observations available to the agent, the actions it chose, and th
arXiv:2609.38755v1 Announce Type: new Abstract: A wide range of approaches have been developed for camera pose estimation, including correspondence-based methods, end-to-end pose regression, and recen
arXiv:2609.39066v1 Announce Type: new Abstract: Conventional image forgery detection methods produce binary scores or pixel-level masks without interpretable evidence, while recent multimodal large la
arXiv:2609.38296v1 Announce Type: new Abstract: Large language models (LLMs) can influence people's beliefs, yet little is known about whether and how they can manipulate each other. To investigate th
Artificial intelligence-driven law firm Arceus Legal today disclosed that it has raised 17 million in funding to expand beyond the commercial contract work it started with. Arceus provides legal servi
arXiv:2609.38737v1 Announce Type: new Abstract: Desk-based learning and creative activities benefit from handwritten engagement. However, current generative AI tools deliver guidance through a separat
arXiv:2609.38445v1 Announce Type: new Abstract: Frontier LLMs are increasingly used to automate scientific research through iterative search. We distinguish idea-driven search from solution-driven sea