Knowledge catalogue
arXiv:2610.08312v1 Announce Type: new Abstract: Continual learning (CL) is essential for Large Language Models (LLMs) to sequentially adapt to evolving tasks. To mitigate catastrophic forgetting, rece
arXiv:2610.07868v1 Announce Type: new Abstract: Large language model agents have been used to search over symbolic structures such as programs and equations. We propose CueRator, an agentic framework
arXiv:2610.07967v1 Announce Type: new Abstract: As large language model (LLM) agents become increasingly autonomous, they may pursue task performance through deception, raising concerns about their re
arXiv:2610.07984v1 Announce Type: cross Abstract: Multimodal assistants answer questions from long-term memories that contain images. After retrieval, each retrieved image reaches the answering model
arXiv:2610.08553v1 Announce Type: cross Abstract: Sequential test-time training adapts a memory network through successive updates, each computing an inner-loop gradient based on the network's previou
arXiv:2610.08722v1 Announce Type: new Abstract: Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's r
arXiv:2610.08674v1 Announce Type: new Abstract: Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independently
arXiv:2610.07603v1 Announce Type: cross Abstract: This article proposes Selective Affective Layer Fine-Tuning (SALFT), an efficient adaptation framework for Video Vision Transformers in player arousal
arXiv:2610.06956v1 Announce Type: new Abstract: Large speech language models have demonstrated strong capabilities in unified cross-modal understanding and generation, yet paralinguistic cues, especia
arXiv:2610.07354v1 Announce Type: new Abstract: Deciding when to escalate a query from a small language model to a larger one requires a cheap signal that predicts, before the large model is called, w
arXiv:2610.08363v1 Announce Type: new Abstract: Maritime systems operate in highly dynamic environments where unexpected equipment failures can compromise safety, reliability, and operational efficien
arXiv:2610.06917v1 Announce Type: new Abstract: Prefill-decode disaggregation is becoming a common architecture for LLM serving because it separates two phases with distinct execution patterns and SLO
arXiv:2610.08639v1 Announce Type: new Abstract: As generated images become increasingly realistic, reliable forgery detection is essential for maintaining trust in visual information. However, existin
arXiv:2610.07447v1 Announce Type: new Abstract: Autoresearch agents tackle open-ended problems by repeatedly proposing candidate solutions, evaluating them, and using feedback to guide subsequent expe
arXiv:2610.05094v1 Announce Type: cross Abstract: Researchers increasingly use Large Language Models as judges (LLM-as-a-judge) to evaluate model outputs. Yet there are no standards for how to design
arXiv:2610.08350v1 Announce Type: cross Abstract: Visual world models enable goal-directed control through decision-time action search, but their deployment efficiency is often limited by conservative
arXiv:2610.07699v1 Announce Type: cross Abstract: Argument Mining (AM) is fundamentally constrained by the scarcity of high-quality structure-annotated datasets. While LLMs have shown promise in synth
arXiv:2601.19595v2 Announce Type: replace-cross Abstract: The deployment of Artificial Intelligence in high-risk domains, such as finance and healthcare, necessitates models that are both fair and tra
arXiv:2610.07638v1 Announce Type: new Abstract: As part of learning to play complex games, human players develop develop abstractions for concepts and strategies of gameplay consistent with game rules
Mistral AI introduced **Mistral Large 4** in October 2026 as a general‑purpose agentic model capable of gathering information and producing final deliverables across complex workflows. The launch high
arXiv:2610.08144v1 Announce Type: cross Abstract: Autoformalisation is increasingly used to verify mathematical texts, including those generated by AI, as in OpenAI's announced proof of blow-up of sol
arXiv:2610.07922v1 Announce Type: cross Abstract: World-action models (WAMs) couple future prediction with robot control, yet existing systems often vary the video backbone, interaction structure, sup
arXiv:2610.08142v1 Announce Type: new Abstract: Zero-shot coordination in embodied settings requires acting while the partner is intermittently out of view, leaving existing methods with ambiguous par
arXiv:2610.07782v1 Announce Type: new Abstract: Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evidence, which matters when KV-cache
arXiv:2511.00053v2 Announce Type: replace-cross Abstract: The design of learning objectives is central to training time-series forecasting models. Existing learning objectives such as mean squared err
arXiv:2602.02140v2 Announce Type: replace Abstract: Recent advances in unified multimodal models (UMM) have demonstrated remarkable progress in both understanding and generation tasks. However, whethe
arXiv:2610.07716v1 Announce Type: new Abstract: Prefill-only decision models inspired by the Jev model score every candidate in a menu during a single forward pass and never decode, which makes one ca
arXiv:2610.07962v1 Announce Type: cross Abstract: Where generalization capacity--the ability to extract context-invariant relational structures--first emerges remains a central question in AI and neur
arXiv:2610.07582v1 Announce Type: new Abstract: Quantitative imaging pipelines can produce precise but systematically different measurements of the same object. We present an empirical reliability ass
arXiv:2610.08137v1 Announce Type: cross Abstract: AI systems create images and videos with image/video generation models or by writing code and graphics descriptions that are then rendered. These rout
arXiv:2610.07834v1 Announce Type: new Abstract: Retrieval-augmented time-series forecasting uses the continuations of historical segments similar to the current context as references for a forecaster.
arXiv:2610.07313v1 Announce Type: new Abstract: Logic programming is increasingly used as the symbolic component of neurosymbolic AI systems. We survey the main rule-based languages in this setting, n
arXiv:2610.07276v1 Announce Type: cross Abstract: Deployment-time safety of language models is commonly implemented through runtime guardrails such as input moderation, routing, retrieval verification
arXiv:2610.07666v1 Announce Type: cross Abstract: This paper presents SENSE, a state-aware framework for generating playable branching visual novels with multi-track emotional navigation. Integrating
arXiv:2610.07237v1 Announce Type: new Abstract: A model that learns from its own outputs inherits more than their correctness: it inherits which solutions it produces. We formulate Looped Self-Distill
arXiv:2511.20718v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks
arXiv:2610.07726v1 Announce Type: new Abstract: Videofluoroscopic Swallowing Study (VFSS) is one of the gold standard for diagnosing swallowing disorders, providing dynamic X-ray imaging of the swallo
arXiv:2609.33678v2 Announce Type: replace Abstract: We introduce SWE-Game, a benchmark of 247 tasks grounded in 41 executable reference Godot games spanning 13 gameplay categories in 2D and 3D. Five t
arXiv:2610.08161v1 Announce Type: cross Abstract: Ambient documentation systems are rapidly gaining adoption, yet their impact on clinical note quality remains poorly characterized. We introduce MedCo
arXiv:2610.06824v2 Announce Type: replace Abstract: We introduce TasteVal, a benchmark to evaluate the experimental research taste of frontier models. We define research taste as the ability to pick i
arXiv:2610.07798v1 Announce Type: new Abstract: People increasingly ask large language models what to do with their money, yet seldom describe their finances in full. This paper asks what a model does
arXiv:2505.17847v3 Announce Type: replace-cross Abstract: Training time-series forecasting models poses unique challenges in loss function design. Most existing approaches adopt temporal mean squared
arXiv:2610.07405v1 Announce Type: new Abstract: pass@k, the fraction of problems a model solves within k sampled attempts, is the field's default protocol for deciding whether reinforcement-learning (
arXiv:2610.07715v1 Announce Type: cross Abstract: A memory system can retire an obsolete value and later restore it merely because the same old statement appears again. A re-read of an old source and
arXiv:2610.07100v1 Announce Type: new Abstract: Persistent agent memory is only as reliable as its retention decision: an assertion weakly supported by its source can be stored and later reused as est
arXiv:2610.07491v1 Announce Type: cross Abstract: When multiple agents share a cost budget, a common Lagrange multiplier can enforce the aggregate constraint but does not determine how its penalty sho
arXiv:2610.06650v2 Announce Type: replace Abstract: Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right ent
arXiv:2610.05779v1 Announce Type: new Abstract: AI-generated videos are rapidly increasing in volume, duration, and resolution, creating growing demands for efficient storage and transmission. Unlike
arXiv:2610.04425v1 Announce Type: new Abstract: Agricultural visual models are typically evaluated for either recognition or localization, but reliable diagnosis requires identifying what is present a
arXiv:2610.04604v1 Announce Type: new Abstract: Automatic curriculum learning can improve the effectiveness of reinforcement learning by selecting the training experiences presented to the agent over
model : add K2 Horizon dense and MoVA support (#29535) model: K2 Horizon gguf conversion code model: loading hparams and tensors in k2-horizon.cpp model: K2 Horizon compute graph model: K2 Horizon com
arXiv:2610.06339v1 Announce Type: new Abstract: Reliable and practical audio-visual DeepFake detection requires benchmarks that reflect diverse linguistic contexts and modern data synthesis pipelines
Standard distillation usually means burning weeks of compute and billions of tokens hoping the student model eventually mimics the teacher. We wanted to see what happens if you skip backprop entirely
arXiv:2610.05590v1 Announce Type: new Abstract: Cold-start drug-drug interaction (DDI) prediction tests whether models can identify clinically significant interactions for drugs without training-time
arXiv:2610.05532v1 Announce Type: cross Abstract: AI agents that send emails, edit files, and make purchases must decide when to act on their own and when to check with the user first. This decision i
arXiv:2610.04159v1 Announce Type: new Abstract: Radiology report generation models can produce fluent text while still containing finding-level inaccuracies. Diagnosis-driven methods improve generatio
arXiv:2610.05207v1 Announce Type: new Abstract: Feed-forward 3D models provide strong multi-view geometric priors, while on- line simultaneous localization and mapping (SLAM) relies mainly on local me
arXiv:2610.05587v1 Announce Type: new Abstract: Individual-level wildlife identification often suffers from data scarcity, as varying observations of the same animal under diverse poses, viewpoints, a
arXiv:2610.05026v1 Announce Type: new Abstract: Vision-language-action (VLA) models encode semantic information from vision-language pretraining, but manipulation also requires precise spatial reasoni
arXiv:2610.06394v1 Announce Type: new Abstract: Human-object interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Traditional supervised methods perform st