Knowledge catalogue
arXiv:2609.24158v1 Announce Type: new Abstract: Reconstructing expressive and relightable 3D head avatars from monocular videos remains challenging in computer vision, as it requires accurate modeling
arXiv:2609.22243v1 Announce Type: new Abstract: Input-conditioned neural interventions raise a runtime question: what persists when one behavioral specification admits multiple actions whose validity
arXiv:2601.15322v3 Announce Type: replace-cross Abstract: Tool-using agents can repeat a final decision while changing their recorded execution. We introduce the Determinism-Faithfulness Assurance Har
arXiv:2609.22208v1 Announce Type: new Abstract: Sofroniew et al. (2026) report that emotion concepts in Claude Sonnet 4.5 are represented as vectors whose geometry mirrors human affect psychology. We
arXiv:2609.22478v1 Announce Type: cross Abstract: Behavioural evaluations of hosted language models can vary because the evaluated service, the measurement instrument, or both differ across runs. We s
arXiv:2609.24057v1 Announce Type: cross Abstract: Medical image interpretation is central to diagnosis and care, yet adapting general-purpose multimodal large language models (MLLMs) often requires re
arXiv:2512.09201v2 Announce Type: replace-cross Abstract: We introduce a framework for converting 3D shapes into compact and editable assemblies of analytic primitives, directly addressing the persist
arXiv:2502.07977v3 Announce Type: replace Abstract: Empirical risk minimization (ERM) is a cornerstone of modern machine learning. This paper focuses on the man-in-the-middle (MITM) attack, wherein ad
arXiv:2609.22359v1 Announce Type: new Abstract: An aligned model asked to hold its answer against a manipulative source must still update on a reliable one and reject an unreliable one: resistance, re
arXiv:2609.23555v1 Announce Type: cross Abstract: Neural video representations (NVRs) represent videos using neural network parameters and, in hybrid formulations, frame-wise latent embeddings. Althou
arXiv:2609.24727v1 Announce Type: new Abstract: Spatial--temporal benchmarks are valid only when their questions, source annotations, and answer options identify the same physical quantity. We audit S
arXiv:2609.23325v1 Announce Type: new Abstract: Single-cell foundation models (scGPT, scBERT, Geneformer) achieve cell-type classification accuracy up to 97.5% in our experiments, yet this aggregate a
arXiv:2609.23967v1 Announce Type: new Abstract: Diffusion models are increasingly adapted from generation to conditional prediction, where a conditioning signal is combined with an evolving noisy repr
arXiv:2609.22988v1 Announce Type: new Abstract: Multilingual code language models transfer skills across programming languages (PLs), but whether any PL occupies a privileged pivot position remains co
arXiv:2609.22283v1 Announce Type: new Abstract: Understanding the design space of streaming video diffusion is essential to exploring its potential for generation quality and computational efficiency.
arXiv:2609.22506v1 Announce Type: new Abstract: Vision Transformers allocate most parameters to multi-layer perceptrons (MLPs) for channel mixing, while token interactions usually rely on quadratic mu
arXiv:2609.23409v1 Announce Type: new Abstract: Cache-based test-time adaptation improves CLIP predictions by storing and retrieving examples from the target stream while keeping the model frozen. How
arXiv:2609.23910v1 Announce Type: new Abstract: Simulation-based evaluation provides a scalable and repeatable alternative to real-world evaluation of vision-language-action (VLA) policies. However, r
arXiv:2609.24850v1 Announce Type: new Abstract: Computing accurate geometry from multi-view images is a fundamental problem in computer vision. Recent feed-forward (FF) models jointly estimate 3D geom
arXiv:2609.22947v1 Announce Type: new Abstract: Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, existi
arXiv:2510.01365v2 Announce Type: replace Abstract: The ability to model mechanics of soft materials under flowing conditions is key in designing and engineering processes and materials with targeted
arXiv:2609.22678v1 Announce Type: cross Abstract: Density-Driven Optimal Control (D2OC) provides an effective framework for steering multi-agent systems toward prescribed spatial distributions. Howeve
Concurrency sweeps help you right-size a generative AI endpoint on Amazon SageMaker AI by systematically benchmarking it at increasing load levels. This post walks through deploying a model, running a
arXiv:2609.23792v1 Announce Type: new Abstract: We consider robotic motion planning and control under unknown dynamics with hybrid state observations, where state measurements are available only in pa
arXiv:2609.23423v1 Announce Type: new Abstract: Vision-language navigation (VLN) has largely been developed for indoor and terrestrial robots, where language can often be treated as a static goal and
arXiv:2410.23912v3 Announce Type: replace-cross Abstract: The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex
arXiv:2609.22547v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) often improves pass@1 while falling behind its base model at larger sampling budgets k, a crosso
arXiv:2609.23457v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is expanding from tasks with well-defined correctness signals, such as mathematics and code, towar
arXiv:2602.03544v2 Announce Type: replace Abstract: Programming a robot arm requires users to interpret coordinate frames, joint rotations, and trajectories that are not directly visible. Augmented re
arXiv:2609.23252v1 Announce Type: cross Abstract: A robot policy is trained with one of two action parameterizations: absolute joint targets, or deltas relative to the current state. The choice is a l
arXiv:2609.23997v1 Announce Type: new Abstract: Multi-robot collaboration could enable more efficient and scalable solutions to complex robotic tasks, but collaboration under partial observability rem
arXiv:2609.24413v1 Announce Type: new Abstract: In this work, we propose a haptic update control law that uses reaction torques to correct axial misalignment during robotic valve manipulation. Unlike
arXiv:2609.22785v1 Announce Type: new Abstract: Market-making strategies in real limit order book markets face substantial model uncertainty and regime-shift risk. Existing adversarial reinforcement l
arXiv:2609.22167v1 Announce Type: new Abstract: Predicting reaction yield from molecular structure and reaction context can cut experimental trial-and-error and speed up condition screening in synthet
arXiv:2609.23432v1 Announce Type: new Abstract: Dynamic rope manipulation is highly sensitive to unknown object dynamics: the same robot motion can produce substantially different responses across rop
arXiv:2502.06726v4 Announce Type: replace-cross Abstract: We derive first-order Pontryagin optimality conditions for stochastic optimal control with deterministic controls for systems modeled by rough
arXiv:2609.23466v1 Announce Type: new Abstract: Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at ever
arXiv:2609.24972v1 Announce Type: cross Abstract: An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding t
arXiv:2609.22258v1 Announce Type: cross Abstract: Large language model-driven remote sensing (RS) agents offer a promising approach to automating geospatial analysis. However, lightweight RS agents ba
arXiv:2609.23427v1 Announce Type: new Abstract: Vision foundation models targeting Earth observation (EO) tasks are commonly evaluated on clean downstream benchmarks, but operational EO products can a
arXiv:2609.23450v1 Announce Type: new Abstract: Accurate cue-ball identification is essential for metric analysis of broadcast snooker. Existing systems evaluate each candidate independently against a
Run GGUF models directly with transformers. This work brings ggml's Metal kernels to the transformers ecosystem, increasing compatibility and performance. More info below Millions of GGUF downloads la
arXiv:2512.11908v3 Announce Type: replace Abstract: Contact-rich tasks pose significant challenges for robotic systems due to inherent uncertainty, complex dynamics, and the high risk of damage during
arXiv:2609.24204v1 Announce Type: new Abstract: Visual segmentation systems encounter objects outside their training distribution during real-world deployment, hindering reliable autonomous systems th
arXiv:2609.22153v1 Announce Type: new Abstract: Methods for addressing safety drift in fine-tuned Large Language Models (LLMs) are scattered across incompatible implementations, lifecycle stages, and
arXiv:2609.24062v1 Announce Type: new Abstract: Hyper-redundant robots are well suited for confined-space manipulation due to their high dexterity, but safe operation in cluttered environments remains
arXiv:2609.23280v1 Announce Type: new Abstract: Safety-critical control under uncertainty requires uncertainty representations that are both statistically valid (for certifiable performance) and compa
arXiv:2609.23773v1 Announce Type: cross Abstract: Decentralised federated learning replaces server aggregation with peer-to-peer model exchange, making collaborator selection a local decision under un
arXiv:2603.08269v2 Announce Type: replace Abstract: In-context imitation learning allows robots to acquire skills from demonstrations, yet one-shot trajectory generation remains fragile under environm
arXiv:2508.03351v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse language tasks, motivating their extension to vision-lan
arXiv:2609.22210v1 Announce Type: new Abstract: SALSA (Semi-Autonomous Literature Summarization Assistant) is an open- source, human-in-the-loop platform for extracting structured scientific datasets
arXiv:2609.22834v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation (OVS) of remote sensing imagery is a challenging pixel-level task requiring strong generalization and adaptation t
arXiv:2609.22576v1 Announce Type: cross Abstract: Semidefinite programming (SDP) certificates for feedback systems containing deep neural networks (NNs) typically scale with the total number of neuron
arXiv:2609.22233v1 Announce Type: new Abstract: Energy systems face converging pressures for security, affordability, resilience, and sustainability, creating a need for faster discovery of deployable
arXiv:2609.24304v1 Announce Type: cross Abstract: Astronomical maps made with different tracers are not expected to have identical morphology. Excitation, optical depth, chemistry, radiation, and ISM
arXiv:2609.23404v1 Announce Type: new Abstract: Point cloud completion aims to infer a complete 3D shape from a partial point cloud and serves as a fundamental building block for downstream tasks such
arXiv:2609.24497v1 Announce Type: new Abstract: Real-time motion planning remains challenging in large and high-dimensional environments. Prior acceleration of RRT* follows tree-centric state organiza
arXiv:2603.02069v2 Announce Type: replace Abstract: We study scaling laws of signSGD under a power-law random features (PLRF) model that accounts for both feature and target decay. We analyze the popu
arXiv:2603.18532v3 Announce Type: replace-cross Abstract: The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fi
arXiv:2609.23263v1 Announce Type: new Abstract: Temporal logic is a formal language for reasoning about system behaviors over time. Signal temporal logic (STL), in particular, has been used to encode