Knowledge catalogue
arXiv:2608.08210v1 Announce Type: new Abstract: Collaborative dialogue can end with apparent agreement while participants still differ on goals, assumptions, or execution plans, creating an extbf{illu
arXiv:2608.07554v1 Announce Type: new Abstract: The development of vision-based wildfire detection systems for unmanned aerial vehicles is constrained by the limited availability of diverse real-world
arXiv:2608.08802v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasi
arXiv:2608.09244v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved remarkable success in generating high-quality images from a given text prompt. Subject-driven generation ai
arXiv:2511.19735v2 Announce Type: replace-cross Abstract: Randomized controlled trials (RCTs)have been the cornerstone of clinical evidence; however, their cost, duration, and restrictive eligibility
arXiv:2608.09420v1 Announce Type: new Abstract: User simulators are widely used as scalable environments for training and evaluating interactive assistants. Generating the next user turn is inherently
arXiv:2604.03919v2 Announce Type: replace-cross Abstract: We present the first systematic study of Sparse Autoencoders (SAEs) on video representations. Standard SAEs decompose video into interpretable
arXiv:2608.08915v1 Announce Type: new Abstract: Situated language use is multimodal and embodied. For example, gestures can carry information that is absent or underspecified in the speech signal, yet
arXiv:2604.05971v2 Announce Type: replace-cross Abstract: Recent research has shown that contrastive vision-language models such as CLIP often lack fine-grained understanding of visual content. While
arXiv:2608.09381v1 Announce Type: new Abstract: Robust robot control benefits from explicitly modeling state transitions, but video-generation world action models (WAMs) introduce substantial deployme
arXiv:2608.08046v1 Announce Type: new Abstract: Text-conditioned chest X-ray generation aims to synthesize realistic radiographs that faithfully depict specified findings. Existing work has primarily
arXiv:2608.07954v1 Announce Type: new Abstract: Large language models can answer knowledge-intensive questions more reliably when they are grounded with knowledge graphs, but systems such as Think-on-
arXiv:2603.07822v2 Announce Type: replace Abstract: Effective human-robot collaboration in open-world environments requires joint planning under uncertainty about the task, the environment, and the hu
arXiv:2608.08598v1 Announce Type: new Abstract: With the continuous improvement of computational capabilities, end-to-end reinforcement learning has been rapidly developed for remotely operated vehicl
arXiv:2608.08805v1 Announce Type: new Abstract: Domain Generalization Semantic Segmentation (DGSS) focuses on generalizing knowledge from labeled source domains to unseen target domains where data is
arXiv:2606.16462v2 Announce Type: replace-cross Abstract: Cross-subject EEG decoding promises more training data, but it also exposes neural networks to strong inter-subject distribution shifts. We st
arXiv:2608.07547v1 Announce Type: cross Abstract: Indoor scene layout generation is a challenging task in interior design. Existing methods often oversimplify the task by reducing room conditions to c
arXiv:2608.08418v1 Announce Type: new Abstract: Leveraging textual information for image clustering has emerged as a promising direction, largely owing to the powerful representations learned by Visio
arXiv:2608.08764v1 Announce Type: cross Abstract: On-policy self-distillation improves language-model reasoning by querying a teacher on states actually visited by the student. Recent methods create a
arXiv:2608.09507v1 Announce Type: cross Abstract: Natural language user preferences provide an interpretable interface for LLM personalization. However, universal preference summaries often contain in
arXiv:2608.00326v2 Announce Type: replace Abstract: Tool calling allows large language models (LLMs) to invoke external computation during problem solving, a useful capability in various fields includ
arXiv:2608.09453v1 Announce Type: cross Abstract: On--off cycling is the main cause of compressor wear in residential heat pumps, yet reinforcement learning (RL) controllers for buildings typically op
arXiv:2604.01414v2 Announce Type: replace Abstract: Vision-based policies have achieved a good performance in robotic manipulation due to the accessibility and richness of visual observations. However
arXiv:2608.08022v1 Announce Type: new Abstract: Recent incidents involving Artificial Intelligence (AI) agents, which were reported escaping their containment `unintentionally' to gain unauthorized ac
arXiv:2503.06211v3 Announce Type: replace-cross Abstract: Text-pretrained language models (LMs) encode rich world knowledge, but adapting them to process and generate perceptual modalities such as aud
arXiv:2608.08494v1 Announce Type: new Abstract: Despite significant advances in Medical Report Generation (MRG), the reliability remains constrained by the prevalence of factual errors. While Direct P
arXiv:2603.00270v3 Announce Type: replace-cross Abstract: Large language models can process millions of tokens, yet how they handle conflicting information within context remains poorly understood. Fr
arXiv:2608.07746v1 Announce Type: new Abstract: Long-horizon humanoid loco-manipulation requires composing versatile whole-body skills and reliable high-level decision making. Existing methods often c
arXiv:2608.07586v1 Announce Type: new Abstract: Semi-supervised Class Incremental Learning (SSCIL) is a severe challenge for neural networks, and it is hardest in the exemplar-free setting where no pa
arXiv:2608.09130v1 Announce Type: cross Abstract: Allocating limited computation among concurrent learning tasks is difficult when each task must reach a target loss before a deadline but its required
arXiv:2608.08176v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) improves the reasoning abilities of LLMs by internalizing privileged context into model parameters through self-disti
arXiv:2608.08220v1 Announce Type: new Abstract: The overlapping disciplines of machine ethics and value alignment are concerned with designing artificial agents that are aligned with human values and
arXiv:2608.08440v1 Announce Type: new Abstract: Cross-subject electroencephalogram (EEG)-based emotion recognition remains challenging due to substantial inter-individual variability and discrete form
arXiv:2608.09836v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement,
arXiv:2608.08606v1 Announce Type: cross Abstract: Machine translation (MT) systems often fail to correctly translate gender, especially when converting from a gender-neutral language like English to a
arXiv:2608.08804v1 Announce Type: cross Abstract: With advancements in long-distance wireless power transfer (WPT) and space-based energy technologies, integrating WPT into non-terrestrial networks (N
arXiv:2608.09057v1 Announce Type: new Abstract: Next-scale visual autoregressive models (VARs) have emerged as a powerful generative paradigm, producing high-quality images through efficient coarse-to
arXiv:2608.09119v1 Announce Type: new Abstract: We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.2 billion activated per token. Each spar
arXiv:2608.08553v1 Announce Type: new Abstract: Video super-resolution (VSR) aims to recover high-fidelity high-resolution videos from low-resolution inputs and is central to applications ranging from
arXiv:2608.07581v1 Announce Type: cross Abstract: Group-based reinforcement learning methods for multimodal large language models typically rely on trajectory-level credit assignment that applies a si
arXiv:2603.02743v4 Announce Type: replace Abstract: Realistic shadow generation is crucial for achieving seamless image compositing, yet existing methods primarily focus on single-object insertion and
arXiv:2608.08567v1 Announce Type: new Abstract: A central obstacle in building graph foundation models is the input heterogeneity in terms of feature space dimensionality, semantics, and structure. Su
arXiv:2608.08607v1 Announce Type: new Abstract: Mental health disorders are a leading cause of disability worldwide, yet Natural Language Processing (NLP) research for mental healthcare has remained c
arXiv:2602.00488v3 Announce Type: replace Abstract: Solving large-scale capacitated vehicle routing problems (CVRP) is hindered by the high complexity of classical heuristics and the limited generaliz
arXiv:2608.07812v1 Announce Type: new Abstract: A host of recent studies have evaluated the cognitive and developmental alignment of Foundation Models (FMs). These investigations include evaluations o
arXiv:2608.08749v1 Announce Type: new Abstract: Long-horizon robot manipulation requires policies to track completed subtasks and critical interaction events. However, existing memory mechanisms heavi
OWN YOUR INTELLIGENCE Last year, building on open-weight models was primarily a cost rationalization exercise. Slightly worse performance for a much cheaper price. Now, it is increasingly an existenti
arXiv:2608.08726v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) uses a privileged teacher to supervise a reasoning model on prefixes sampled from its own rollouts. Yet each rollou
arXiv:2510.22028v4 Announce Type: replace Abstract: Quality Estimation (QE) metrics are vital in machine translation for reference-free evaluation and increasingly serve as selection criteria in data
arXiv:2608.09931v1 Announce Type: new Abstract: Self-improvement for multimodal large language models (MLLMs) is typically driven by reward-based methods that provide only coarse scalar feedback. Dist
arXiv:2608.07681v1 Announce Type: new Abstract: Accurate and robust time series forecasting is essential in many applications involving physical processes, such as manufacturing monitoring and astroph
arXiv:2508.01718v2 Announce Type: replace Abstract: We develop a physics-informed policy-iteration method for stationary second-order Hamilton--Jacobi--Bellman equations arising in continuous-time sto
arXiv:2608.07509v1 Announce Type: cross Abstract: LLMs are increasingly used for conversational tutoring, but effective tutoring requires more than correct answers. Tutors must choose when to scaffold
I am working on an AI for a small single-player merge puzzle and would appreciate pointers to related algorithms, papers, or existing implementations. It resembles 2048 in its action -> afterstate ->
arXiv:2608.08869v1 Announce Type: new Abstract: Large language models are increasingly used for ordinal classification, yet semantically equivalent changes to prompt organization can alter their predi
arXiv:2608.08245v1 Announce Type: cross Abstract: LLM applications deployed at scale face a fundamental challenge: privacy constraints prevent direct inspection of user interactions, making it difficu
arXiv:2608.07913v1 Announce Type: cross Abstract: Selective-risk certificates promise that accepted outputs meet a declared error target. We develop Fed-SRC, a score-agnostic certificate for federated
arXiv:2608.09263v1 Announce Type: new Abstract: Outcome verifiers score completed reasoning traces but do not assign credit to intermediate tokens. Privileged self-distillation attempts to fill this g
arXiv:2608.09228v1 Announce Type: cross Abstract: On-Policy Self-Distillation (OPSD) is commonly interpreted as the transfer of privileged information: a teacher observes the verified solution to the
arXiv:2607.11505v2 Announce Type: replace-cross Abstract: Post-training for large language models typically couples policy exploration with model optimization, hindering the reuse of high-reward behav