Knowledge catalogue
arXiv:2605.09549v1 Announce Type: new Abstract: Adaptive prompting mechanisms have been proposed to enhance vision-language models by dynamically tailoring prompts to inputs. However, in frozen few-sh
arXiv:2605.08828v1 Announce Type: new Abstract: Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations i
arXiv:2602.06286v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in high-stakes settings where good decisions require forming beliefs over the probability of
arXiv:2605.06033v2 Announce Type: replace-cross Abstract: The extent to which Artificial Intelligence (AI) can trigger generalized paradigm shifts in science is unclear. Although some of these technol
arXiv:2605.09109v1 Announce Type: new Abstract: Many continuous-control problems ship with a competent but suboptimal controller (a tuned PID, a hand-designed gait). A growing family of methods uses s
arXiv:2605.08933v1 Announce Type: new Abstract: Muon orthogonalizes matrix updates, but multi-head attention naturally operates at the level of heads. This granularity mismatch raises the question of
arXiv:2605.08318v1 Announce Type: cross Abstract: We study the problem of architecture selection for deep learning models trained to solve partial differential equations (PDEs), asking when transforme
arXiv:2605.10659v1 Announce Type: cross Abstract: Digital personas powered by Large Language Models (LLMs) are increasingly proposed as substitutes for human survey respondents, yet it remains unclear
arXiv:2605.08710v1 Announce Type: new Abstract: Human-AI teams fail to outperform their best member in 70% of studies, yet no theory specifies when complementarity is achievable. We derive tight bound
arXiv:2605.08460v1 Announce Type: cross Abstract: Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems th
arXiv:2605.10236v1 Announce Type: cross Abstract: Modern off-policy reinforcement learning algorithms often rely on simple uniform replay sampling and it remains unclear when and why non-uniform repla
arXiv:2605.08234v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by the memory and bandwidth cost of reading large KV caches during decoding. KV compression reduces this co
arXiv:2602.02821v2 Announce Type: replace Abstract: Much recent work has argued that the variation in the languages of the world can be explained from the perspective of efficient communication; in pa
arXiv:2605.09460v1 Announce Type: cross Abstract: Identity-preserved image generation is typically built on many-step diffusion backbones, making personalized generation expensive at deployment time.
arXiv:2605.08478v1 Announce Type: new Abstract: We study how to allocate inference-time compute for competitive programming under fixed budgets. Evaluating 216 Codeforces problems across Divisions 1-3
arXiv:2605.08245v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate,
arXiv:2411.18111v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) that incorporate visual models and large language models have achieved impressive results across cross-modal un
arXiv:2602.09789v3 Announce Type: replace Abstract: Scaling up model parameters has long been a prevalent training paradigm driven by the assumption that larger models yield superior generation capabi
arXiv:2605.08992v1 Announce Type: new Abstract: Federated learning (FL) is increasingly used to fine-tune foundation models (FMs) on distributed private data. The community largely assumes that large-
arXiv:2605.10242v1 Announce Type: cross Abstract: Unsupervised tabular anomaly detection methods typically learn feature patterns from normal samples during training and subsequently identify samples
arXiv:2605.10176v1 Announce Type: cross Abstract: Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that ena
arXiv:2605.10171v1 Announce Type: cross Abstract: Scientific peer reviews frequently contain conflicting expert judgments, and the increasing scale of conference submissions makes it challenging for A
arXiv:2605.09030v1 Announce Type: new Abstract: Raw cosine in the 768-dimensional output space of the Contrastive Style Descriptor (CSD) is now widely read as an absolute, calibrated style-fidelity sc
arXiv:2512.08875v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have recently demonstrated remarkable performance in generating high-quality tabular synthetic data. In practice,
arXiv:2605.09860v1 Announce Type: new Abstract: Long-horizon reasoning requires deciding not only what actions to take, but how deeply to commit before the next observation. We formalize this as commi
arXiv:2605.06222v2 Announce Type: replace-cross Abstract: World Action Models (WAMs) have recently emerged as a promising paradigm for robotic manipulation by jointly predicting future visual observat
arXiv:2605.10605v1 Announce Type: new Abstract: Expressions with an aspectual variant of a light verb, e.g. 'take on debt' vs. 'have debt', are frequent in texts but often difficult to classify betwee
arXiv:2603.10051v2 Announce Type: replace-cross Abstract: Self-supervised masked modeling shows promise for encrypted traffic classification by masking and reconstructing raw bytes. Yet recent work re
arXiv:2507.03167v3 Announce Type: replace-cross Abstract: Chat models without chain-of-thought (CoT) reasoning must decide whether to refuse a harmful request before generating their first response to
arXiv:2605.10544v1 Announce Type: new Abstract: Long-context adaptation is often viewed as window scaling, but this misses a token-level supervision mismatch: in packed training with document masking,
arXiv:2605.08200v1 Announce Type: new Abstract: A pervasive intuition holds that vision-language models (VLMs) are most trustworthy when their attention maps look sharp: concentrated attention on the
arXiv:2601.21739v2 Announce Type: replace-cross Abstract: Adam has been at the core of large-scale training for almost a decade, yet a simple empirical fact remains unaccounted for: both validation sc
arXiv:2605.08878v1 Announce Type: cross Abstract: Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representa
arXiv:2605.08250v1 Announce Type: cross Abstract: Recent advances in diffusion transformers (DiTs) have enabled promising single-turn image editing capabilities. However, multi-turn editing often lead
arXiv:2604.02564v2 Announce Type: replace-cross Abstract: We present MaskGen, a theoretically grounded and deliberately simple approach for domain generalization in 3D biomedical image segmentation. M
arXiv:2502.10760v2 Announce Type: replace Abstract: Frontier models can be prompted or conditioned to do many tasks, but finding good prompts is not always easy, nor is understanding some performant p
arXiv:2605.10714v1 Announce Type: cross Abstract: Cross-lingual transfer has become a central paradigm for extending natural language processing (NLP) technologies to low-resource languages. By levera
arXiv:2605.08563v1 Announce Type: new Abstract: When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the ne
arXiv:2605.10658v1 Announce Type: new Abstract: Continual learning requires new-task adaptation without damaging previously acquired capabilities. Recent forward-pass and zeroth-order (ZO) results sho
arXiv:2605.10912v1 Announce Type: new Abstract: Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However,
arXiv:2603.23806v2 Announce Type: replace-cross Abstract: AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invoca
arXiv:2605.09511v1 Announce Type: new Abstract: Many downstream decisions in complex terrain require fast wind estimates at a small number of user-specified locations and heights for a given forecast
arXiv:2605.09765v1 Announce Type: cross Abstract: Representation learning in electronic health records (EHR) has largely followed paradigms inherited from natural language processing, relying on seque
arXiv:2605.09650v1 Announce Type: new Abstract: Modern agents built on frontier language models often cannot adapt their weights. What, then, remains trainable? We argue it is the agent's workspace, t
arXiv:2605.10434v1 Announce Type: new Abstract: Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving i
arXiv:2605.09167v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) performs well for high-resource languages with abundant paired audio-transcript data, but its accuracy degrades sha
arXiv:2605.05611v2 Announce Type: replace-cross Abstract: In this paper, we present X-Voice, a 0.4B multilingual zero-shot voice cloning model that clones arbitrary voices and enables everyone to spea
arXiv:2605.10704v1 Announce Type: cross Abstract: This paper introduces a proactive Unmanned Aerial Vehicle (UAV) mobility management xApp for Open Radio Access Network (O-RAN) Near Real-Time Radio In
arXiv:2605.08842v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models organize knowledge into explicitly routed expert modules, making expert-level representations traceable and ana
arXiv:2605.10734v1 Announce Type: new Abstract: For reinforcement learning in the real world online exploration is expensive A common practice in robotic reinforcement learning is to incorporate addit
arXiv:2605.09639v1 Announce Type: cross Abstract: While U-Net architectures remain the gold standard for medical image segmentation, their deployment in resource-constrained environments demands aggre
arXiv:2605.09981v1 Announce Type: cross Abstract: Multimodal models that jointly reason over protein sequences, structures, and function annotations within a unified representation hold immense potent
arXiv:2605.06231v2 Announce Type: replace Abstract: This paper presents our system for SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization, which identifies p
arXiv:2605.09842v1 Announce Type: new Abstract: While machine learning has revolutionized many fields such as natural language processing (NLP) and computer vision, its impact on time-series forecasti
arXiv:2510.03761v2 Announce Type: replace-cross Abstract: The widespread use of preprint repositories such as arXiv has accelerated the communication of scientific results but also introduced overlook
arXiv:2508.11070v2 Announce Type: replace Abstract: Decision makers are increasingly relying on machine learning in sensitive situations. Algorithmic recourse aims to provide individuals with actionab
arXiv:2605.09360v1 Announce Type: cross Abstract: Execution-based evaluation of LLM-generated code implicitly treats successful execution as a proxy for correctness. In scientific simulation, this pro
arXiv:2603.25074v2 Announce Type: replace Abstract: Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Ne
arXiv:2605.08560v1 Announce Type: cross Abstract: We present ZAYA1-VL-8B, a compact mixture-of-experts vision-language model built upon our in-house language model, ZAYA1-8B. Despite its compact size,
arXiv:2605.08814v1 Announce Type: new Abstract: Chinese character categories are extremely large, and unseen characters frequently arise in open-world scenarios, making zero-shot Chinese character rec