Knowledge catalogue
arXiv:2610.13267v1 Announce Type: new Abstract: Large language model (LLM) agents are highly vulnerable to memory-poisoning attacks. Existing defenses primarily rely on external modules for either sta
arXiv:2610.13806v1 Announce Type: cross Abstract: Production recommender systems have feature-lifecycle asymmetry: adding new features must produce gains on some metric, while feature removal must not
arXiv:2610.13117v1 Announce Type: new Abstract: Vision-language-action (VLA) models and world action models (WAMs) have advanced robotic policy learning by building on pretrained vision-language model
arXiv:2610.13102v1 Announce Type: new Abstract: Broadcast archives offer scale and diversity for self-supervised learning (SSL) but contain substantial noisy, non-speech, and multilingual content. Pri
arXiv:2610.06411v2 Announce Type: replace Abstract: Agentic systems increasingly coordinate molecular-design tools, but it is unclear which layer of the stack limits outcomes on real projects. We deve
arXiv:2610.12946v1 Announce Type: cross Abstract: Comparing distributions under severe sample imbalance requires effectively using abundant majority observations while retaining sensitivity to differe
arXiv:2604.02563v2 Announce Type: replace Abstract: Robots that traverse natural terrain must interpret contact forces generated under highly dynamic conditions. However, most terrain characterization
arXiv:2610.13768v1 Announce Type: cross Abstract: What can an adversary recover from a model trained with DP-SGD? Its (arepsilon,elta) guarantee does not answer this question directly. We derive a dis
arXiv:2610.13375v1 Announce Type: new Abstract: Rubrics have been widely used to evaluate and optimize language models on open-ended tasks. However, existing work primarily focuses on generating bette
arXiv:2610.12793v1 Announce Type: new Abstract: Pretrained vision-language-action (VLA) policies fail on memory tasks, behaviour that depends on events observed long before the current frame, because
arXiv:2610.12990v1 Announce Type: new Abstract: We study how offline data can help online learning in stochastic linear bandits. We focus on partially covered offline data, where only k of the d featu
arXiv:2610.12894v1 Announce Type: cross Abstract: Determinantal point processes (DPPs) model subset selection probability with repulsion, but many applications also exhibit attraction arising from pai
arXiv:2610.13015v1 Announce Type: cross Abstract: Reinforcement learning has become the foundational paradigm for enhancing the reasoning capabilities of LLMs. Yet the dominant approach, Proximal Poli
arXiv:2610.12669v1 Announce Type: cross Abstract: Large language models are becoming central to GeoAI systems, yet their evaluation rarely considers the elicitation of geospatial data requirements. Th
arXiv:2610.13035v1 Announce Type: cross Abstract: Multi-view representations enable pretrained image and video vision-language models to understand 3D scenes, but their long visual token sequences mak
arXiv:2610.13773v1 Announce Type: cross Abstract: Multiple-gradient descent is typically formulated in Euclidean geometry, whereas matrix-aware optimizers use directions induced by other norms. We ana
arXiv:2610.12617v1 Announce Type: new Abstract: Geopolitical and strategic intelligence reports constitute a rich source of expert knowledge and have increasing value in the current political climate,
arXiv:2610.12904v1 Announce Type: new Abstract: Tabular foundation models (TFMs) based on prior-data fitted networks typically use sampled hard query labels, leaving avoidable sampling variability in
arXiv:2601.13600v2 Announce Type: replace Abstract: NLP systems increasingly aggregate claims from retrieved passages, documents, and generated reasoning steps. Yet current factuality methods mostly v
arXiv:2610.12528v1 Announce Type: new Abstract: Continuous glucose monitoring (CGM) foundation models encode each day as one vector that mixes who the person is, what happened that day and how the sen
arXiv:2610.13923v1 Announce Type: cross Abstract: Deep-space communications operate under intermittent connectivity, long propagation delays, and relay storage constraints. In such networks, the Bundl
arXiv:2610.13217v1 Announce Type: cross Abstract: Video generation supports digital content creation, with applications in virtual avatars, AI-driven filmmaking, interactive game engines, and world mo
arXiv:2610.12609v1 Announce Type: new Abstract: Humanoid and service robots operating in clut- tered human environments may encounter motion planning problems that are infeasible when all surrounding
arXiv:2610.06354v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly explored for graph understanding and decision-making, while System One models such as Jev select direc
arXiv:2610.13164v1 Announce Type: new Abstract: Scaling robot manipulation policies requires large amounts of diverse, action-labeled data, yet collecting such data in the real world remains expensive
arXiv:2511.01047v4 Announce Type: replace-cross Abstract: Automated program repair (APR) has recently shifted toward large language models and agent-based systems, while prior work shows that reposito
arXiv:2610.13477v1 Announce Type: cross Abstract: We derive approximation rates for Sobolev functions defined on the complex unit sphere and complex projective space, representing quantum states, and
arXiv:2610.12883v1 Announce Type: new Abstract: Non-autoregressive multi-step forecasting (NAF) enables time series foundation models to predict an entire future horizon in a single forward pass. Desp
arXiv:2505.11304v4 Announce Type: replace-cross Abstract: Federated learning (FL) commonly involves clients with diverse communication and computational capabilities. Such heterogeneity can significan
arXiv:2610.13350v1 Announce Type: new Abstract: Widely reused preprocessing pipelines for electronic health records can encode assumptions about when information became available, what clinical episod
arXiv:2610.13935v1 Announce Type: cross Abstract: Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods in
arXiv:2610.13000v1 Announce Type: new Abstract: Language-model agents are used for specialized work such as financial research, healthcare and law. Such agents are often capable enough for a task but
arXiv:2610.13901v1 Announce Type: cross Abstract: We study the last iterate of standard asynchronous Q-learning from a single trajectory of a finite Markov decision process. The trajectory follows a f
arXiv:2610.13849v1 Announce Type: new Abstract: We present HorizonNav, a video diffusion-based framework for anticipatory robot navigation that transforms a single RGB image and a text prompt into a g
arXiv:2610.13321v1 Announce Type: new Abstract: Web crawling is a major source of large language model (LLM) pretraining data, yet data-selection pipelines discard a large share of crawled pages. We i
arXiv:2610.13208v1 Announce Type: new Abstract: Time-series foundation models use the same network depth for every input, although forecasting windows differ in structure and difficulty. We test wheth
arXiv:2610.13236v1 Announce Type: cross Abstract: Recent advances have significantly improved the performance of Abstract Meaning Representation (AMR) parsers, yet determining when their outputs can b
arXiv:2610.13764v1 Announce Type: cross Abstract: Prior-data fitted networks (PFNs) are trained to approximate the Bayesian posterior predictive distribution (PPD) of a synthetic prior, yet results ab
arXiv:2610.13082v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being explored as facilitators of group discussion and collaborative work, but the behavioral differences
arXiv:2610.13119v1 Announce Type: new Abstract: Collecting dexterous manipulation demonstrations for each robot hand requires repeated task-specific data acquisition. We ask whether one shared corpus
arXiv:2610.13494v1 Announce Type: new Abstract: Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnes
arXiv:2610.13632v1 Announce Type: new Abstract: Large language model (LLM) agents are rapidly improving on long-horizon scientific and olympiad tasks. Recent systems have produced a Lean-formalized re
arXiv:2602.02473v2 Announce Type: replace-cross Abstract: Enabling humanoid robots to perform agile and adaptive interactions has long been a core challenge in robotics. Current approaches are bottlen
arXiv:2609.35328v2 Announce Type: replace Abstract: Meta-Black-Box Optimization (MetaBBO) is one of the highlights in the recent AI for Optimization trend. This paradigm's bi-level workflow leverages
arXiv:2610.12631v1 Announce Type: new Abstract: Recently, soft robotic procedures are being developed aiming at achieving targeted minimally invasive operations or drug administration in specific loca
arXiv:2610.13411v1 Announce Type: cross Abstract: Traditional system identification typically involves two steps: initially, training data is processed to estimate a model of the system of interest; t
arXiv:2610.12666v1 Announce Type: cross Abstract: We introduce iRAG, a human-in-the-loop decision-support system combining Retrieval-Augmented Generation (RAG) with Hybrid Decision-Making. Unlike conv
arXiv:2610.13844v1 Announce Type: new Abstract: Generative molecular design typically relies on over-generation and post-hoc filtering. Inference-time steering methods like Feynman-Kac (FK) steering i
arXiv:2602.18655v3 Announce Type: replace Abstract: For fully actuated rigid robots, kinematic inversion is a purely geometric problem, efficiently solved by closed-loop inverse kinematics (CLIK) sche
arXiv:2511.10383v2 Announce Type: replace-cross Abstract: Continuous-time stochastic processes underlie many natural and engineered systems. In healthcare, autonomous driving, and industrial control,
arXiv:2610.13672v1 Announce Type: cross Abstract: Large language models struggle to reliably identify and correct errors in their own reasoning. Unlike prior training-based approaches that fine-tune a
arXiv:2410.03043v3 Announce Type: replace Abstract: Current research on deep machine unlearning primarily focuses on improving or evaluating the overall effectiveness of unlearning methods while overl
arXiv:2610.12820v1 Announce Type: new Abstract: The shock response spectrum (SRS) characterizes the peak responses of single-degree-of-freedom systems to transient acceleration. Because the mapping fr
arXiv:2610.13194v1 Announce Type: new Abstract: Long-horizon autonomous research has shown promise in accelerating scientific progress through sustained cycles of hypothesis generation, implementation
arXiv:2610.13315v1 Announce Type: cross Abstract: This paper considers channel state information (CSI) prediction using neural networks for time-varying multi-antenna channels from noisy historical ob
arXiv:2610.13628v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies issue sparse targets whose arrival at the robot controller is delayed and irregular, so a reasonable predicted a
arXiv:2610.12957v1 Announce Type: cross Abstract: Embodied agents must translate multimodal observations and user requests into executable actions while adapting to product constraints, changing goals
arXiv:2610.12495v1 Announce Type: cross Abstract: Small language models trained on a single local machine leave little room for architectural trial and error. Kairos combines bidirectional gated-Delta
arXiv:2610.13625v1 Announce Type: cross Abstract: The external validity of a study is the extent to which its findings generalize to unseen experimental conditions, such as datasets. We formalize the
arXiv:2610.12737v1 Announce Type: new Abstract: Gradient-based attribution provides input-specific information about model parameters, but computing it via backpropagation for many samples is expensiv