Knowledge catalogue
arXiv:2510.04548v2 Announce Type: replace-cross Abstract: In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It
arXiv:2603.00110v2 Announce Type: replace Abstract: The scarcity of large-scale robotic data has motivated the repurposing of foundation models from other modalities for policy learning. In this work,
arXiv:2604.21794v1 Announce Type: new Abstract: Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and or
arXiv:2505.15269v2 Announce Type: replace Abstract: Recent developments in Video Large Language Models (Video LLMs) have enabled models to process hour-long videos and exhibit exceptional performance.
arXiv:2604.21924v1 Announce Type: new Abstract: Long-horizon manipulation remains challenging for vision-language-action (VLA) policies: real tasks are multi-step, progress-dependent, and brittle to c
arXiv:2511.18513v2 Announce Type: replace Abstract: Deep unfolding networks (DUNs) have achieved remarkable success and become the mainstream paradigm for spectral compressive imaging (SCI) reconstruc
arXiv:2510.18731v2 Announce Type: replace-cross Abstract: Large Language Models demonstrate strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC), a degra
arXiv:2604.21370v1 Announce Type: new Abstract: We present a systematic study of multilingual polarization detection across 22 languages for SemEval-2026 Task 9 (Subtask 1), contrasting multilingual g
arXiv:2604.21096v1 Announce Type: cross Abstract: Tip-of-the-Tongue (ToT) retrieval benchmarks have largely focused on English, limiting their applicability to multilingual information access. In this
arXiv:2604.21138v1 Announce Type: cross Abstract: Multi-robot control in cluttered environments is a challenging problem that involves complex physical constraints, including robot-robot collisions, r
arXiv:2604.21896v1 Announce Type: new Abstract: This paper introduces a new paradigm for AI game programming, leveraging large language models (LLMs) to extend and operationalize Claude Shannon's taxo
arXiv:2604.21753v1 Announce Type: cross Abstract: Simulations of crystal growth are performed by using Convolutional Recurrent Neural Network surrogate models, trained on a dataset of time sequences c
arXiv:2601.20706v2 Announce Type: replace-cross Abstract: Diffusion-based LLMs (dLLMs) fundamentally depart from traditional autoregressive (AR) LLM inference: they leverage bidirectional attention, b
OpenAI's GPT-5.5 model is now available on Databricks' platform with governance capabilities provided through Unity AI Gateway, enabling enterprises to deploy and manage the model within their data in
arXiv:2601.15984v2 Announce Type: replace Abstract: We introduce extsc{k-lazyGD}, an online learning algorithm that bridges the gap between greedy Online Gradient Descent (OGD, for k{=}1) and lazy GD/
arXiv:2604.21706v1 Announce Type: new Abstract: We previously introduced a training-free method for dysarthria severity assessment based on d-prime separability of phonological feature subspaces in fr
arXiv:2604.21253v1 Announce Type: cross Abstract: While LLMs demonstrate remarkable fluency in narrative generation, existing methods struggle to maintain global narrative coherence, contextual logica
arXiv:2604.21313v1 Announce Type: new Abstract: Accurate quantification of the physical exposure area of beach litter, rather than simple item counts, is essential for credible ecological risk assessm
arXiv:2604.21100v1 Announce Type: new Abstract: To address the increasing long-context compute limitations of softmax attention, several subquadratic recurrent operators have been developed. This work
arXiv:2604.21481v1 Announce Type: new Abstract: Crowdsourced pairwise evaluation has emerged as a scalable approach for assessing foundation models. However, applying it to Text to Speech(TTS) introdu
arXiv:2604.21191v1 Announce Type: new Abstract: Prefix parsing asks whether an input prefix can be extended to a complete string generated by a given grammar. In the weighted setting, it also provides
arXiv:2604.21104v1 Announce Type: new Abstract: New geospatial foundation models introduce a new model architecture and pretraining dataset, often sampled using different notions of data diversity. Pe
arXiv:2604.21337v1 Announce Type: new Abstract: In this paper, we aim to extend the traditional point-mass-like robot representation in swarm robotics and instead study a swarm of long Heavy Articulat
arXiv:2106.01254v3 Announce Type: replace Abstract: In many classification tasks, there is no definitive ground truth, only human judgments that may disagree. We address two challenges that arise in s
arXiv:2604.21556v1 Announce Type: new Abstract: The problem of probabilistic verification of a neural network investigates the probability of satisfying the safe constraints in the output space when t
arXiv:2604.21611v1 Announce Type: cross Abstract: Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs). We introduce a fourt
arXiv:2604.21728v1 Announce Type: new Abstract: Pretrained vision-language models such as CLIP exhibit strong zero-shot generalization but remain sensitive to distribution shifts. Test-time adaptation
arXiv:2604.20860v1 Announce Type: cross Abstract: Despite the success of Retrieval-Augmented Generation (RAG) in grounding LLMs with external knowledge, its application over heterogeneous sources (e.g
arXiv:2604.21249v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) enable high-level semantic reasoning for end-to-end autonomous driving, particularly in unstructured environments, e
arXiv:2604.21232v1 Announce Type: new Abstract: Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-
arXiv:2604.05673v2 Announce Type: replace-cross Abstract: Visual navigation is a core challenge in Embodied AI, requiring autonomous agents to translate high-dimensional sensory observations into cont
arXiv:2604.21160v1 Announce Type: new Abstract: Point-Vision-Language Models promise to empower embodied agents with executable spatial reasoning, yet they frequently succumb to geometric hallucinatio
arXiv:2604.20904v1 Announce Type: cross Abstract: Information handling practices of LLM agents are broadly misaligned with the contextual privacy expectations of their users. Contextual Integrity (CI)
arXiv:2510.20505v4 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) remains brittle on multi-step questions and heterogeneous evidence sources, trading accuracy against late
arXiv:2604.21776v1 Announce Type: new Abstract: Precise camera control for reshooting dynamic videos is bottlenecked by the severe scarcity of paired multi-view data for non-rigid scenes. We overcome
arXiv:2604.21478v1 Announce Type: new Abstract: Nowadays, visual data forgery detection plays an increasingly important role in social and economic security with the rapid development of generative mo
arXiv:2604.21893v1 Announce Type: cross Abstract: Geographic context is often consider relevant to motor insurance risk, yet public actuarial datasets provide limited location identifiers, constrainin
arXiv:2604.21882v1 Announce Type: new Abstract: Understanding what kinds of factual knowledge large language models (LLMs) memorize is essential for evaluating their reliability and limitations. Entit
arXiv:2601.09253v2 Announce Type: replace-cross Abstract: While Supervised Fine-Tuning (SFT) and Rejection Sampling Fine-Tuning (RFT) are standard for LLM alignment, they either rely on costly expert
arXiv:2604.20851v1 Announce Type: cross Abstract: Modern video-text retrieval (VTR) models excel on in-distribution benchmarks but are highly vulnerable to real-world query shifts, where the distribut
arXiv:2604.21409v1 Announce Type: new Abstract: We present S1-VL, a multimodal reasoning model for scientific domains that natively supports two complementary reasoning paradigms: Scientific Reasoning
arXiv:2503.17239v3 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) is a common practice to adapt generalist models to specialized domains. However, recent studies show
arXiv:2509.19318v2 Announce Type: replace-cross Abstract: While robotic perception has advanced rapidly in vision and touch, enabling robots to reason about indoor fungal contamination from weak, diff
arXiv:2512.19995v2 Announce Type: replace-cross Abstract: Large language models increasingly expose reasoning traces, yet their underlying cognitive structure and steps remain difficult to identify an
arXiv:2604.21592v1 Announce Type: new Abstract: Recent breakthroughs in 3D generative modeling have yielded remarkable progress in static shape synthesis, yet high-fidelity dynamic 4D generation remai
arXiv:2604.21926v1 Announce Type: new Abstract: Understanding human activities and their surrounding environments typically relies on visual perception, yet cameras pose persistent challenges in priva
arXiv:2604.21782v1 Announce Type: new Abstract: We present the shared task on narrative similarity and narrative representation learning - NSNRL (pronounced 'nass-na-rel'). The task operationalizes na
arXiv:2604.21016v1 Announce Type: cross Abstract: When training neural networks with full-batch gradient descent (GD) and step size eta, the largest eigenvalue of the Hessian -- the sharpness S(oldsym
arXiv:2604.21231v1 Announce Type: cross Abstract: Efficient inference for on-device Large Language Models (LLMs) remains challenging due to limited hardware resources and the high cost of the prefill
arXiv:2604.21094v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) excel on relational data, but standard benchmarks unrealistically assume the graph is centrally available. In practice, set
arXiv:2604.21700v1 Announce Type: cross Abstract: The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studie
arXiv:2604.21282v1 Announce Type: cross Abstract: Automated code vulnerability detection is critical for software security, yet existing approaches face a fundamental trade-off between detection accur
arXiv:2604.21748v1 Announce Type: cross Abstract: Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasonin
arXiv:2511.03325v3 Announce Type: replace Abstract: Video Question Answering (VideoQA) in the surgical domain aims to enhance intraoperative understanding by enabling AI models to reason over temporal
arXiv:2503.16416v2 Announce Type: replace Abstract: LLM-based agents represent a paradigm shift in AI, enabling autonomous systems to plan, reason, and use tools while interacting with dynamic environ
arXiv:2604.21031v1 Announce Type: cross Abstract: Synthetic data generation offers promise for addressing data scarcity and privacy concerns in educational technology, yet practitioners lack empirical
arXiv:2604.21806v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) is an important image retrieval paradigm that enables users to retrieve a target image using a multimodal query that cons
arXiv:2604.21324v1 Announce Type: new Abstract: Visible-infrared person re-identification (VI-ReID) enables cross-modality identity matching for all-day surveillance, yet existing methods predominantl
arXiv:2604.21930v1 Announce Type: new Abstract: Streaming Continual Learning (CL) typically converts a continuous stream into a sequence of discrete tasks through temporal partitioning. We argue that
arXiv:2604.20569v1 Announce Type: cross Abstract: Automatic systems are increasingly used to assess the originality of responses in creative tasks. They offer a potential solution to key limitations o