On the Complexity of Preference-Based Bandits
arXiv:2609.39351v1 Announce Type: new Abstract: We study preference-based bandits with general reward function classes, where a learner sequentially selects pairs of arms and observes binary preferenc
Knowledge catalogue
arXiv:2609.39351v1 Announce Type: new Abstract: We study preference-based bandits with general reward function classes, where a learner sequentially selects pairs of arms and observes binary preferenc
arXiv:2609.38860v1 Announce Type: cross Abstract: Learning from human preferences is central to large language model (LLM) alignment, but human preference annotation is costly. Active preference learn
arXiv:2609.34284v2 Announce Type: replace Abstract: Personalized LLMs must decide, for each stored preference, whether the current context calls for applying or suppressing it, which we call its appli
arXiv:2609.38466v1 Announce Type: new Abstract: Text-conditioned full-body human-object interaction (HOI) generation requires synthesizing human motion and object trajectories that match the input tex
arXiv:2609.38715v1 Announce Type: new Abstract: This paper proposes a control strategy for path following that is model-free and relies solely on deceleration for skid-steering planetary rovers naviga
arXiv:2609.40118v1 Announce Type: new Abstract: As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compac
arXiv:2609.38490v1 Announce Type: cross Abstract: Large language model (LLM) agents that reason over clinical records must track changes in a patient's state while preserving the history needed to und
arXiv:2609.38926v1 Announce Type: cross Abstract: Long-term precipitation nowcasting requires modeling radar-echo evolution while preserving localized high-intensity structures. Recent radar-specific
arXiv:2609.40185v1 Announce Type: new Abstract: Constrained generation aims to sample from language models (LMs) conditioned on hard constraints. Existing constrained-generation techniques for nondete
arXiv:2609.38971v1 Announce Type: cross Abstract: Embodied vision-language models (VLMs) are increasingly deployed as high-level planners for robots because they generalize across diverse environments
arXiv:2609.38538v1 Announce Type: cross Abstract: Random splitting can yield non-independent train--test subsets when a dataset contains related samples, as is common in certain applications such as b
arXiv:2609.38833v1 Announce Type: new Abstract: Federated continual learning must integrate new tasks over time without losing earlier-task knowledge. Most existing methods attach an anti-forgetting m
arXiv:2609.38578v1 Announce Type: cross Abstract: Cross-structural motion retargeting aims to transfer motion between different skeletal topologies. Despite recent progress, existing state-of-the-art
arXiv:2609.39007v1 Announce Type: cross Abstract: Sessionized interaction histories contain behavioral patterns that can improve sequential recommendation. However, existing models process all session
arXiv:2609.39788v1 Announce Type: new Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and
arXiv:2609.39635v1 Announce Type: new Abstract: Given a target dataset, such as faces with eyeglasses, and a background dataset, such as faces without, contrastive analysis separates extit{salient} fa
arXiv:2609.39679v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) must remain effective when new spoofing attacks emerge after deployment. Emerging audio language model (ALM)-based ADD
arXiv:2609.39623v1 Announce Type: new Abstract: The proliferation of high-fidelity generative editing models has made it possible to inject violent or sexual content into otherwise ordinary images whi
arXiv:2609.39645v1 Announce Type: cross Abstract: Multi-agent collaboration lets large language models (LLMs) improve question answering through deliberation and feedback. Yet shared discussion couple
arXiv:2609.38287v1 Announce Type: cross Abstract: Simulation-augmented generation (SAGE) is a recent technical proposal in which models simulate individuals' viewpoints at inference time in order to p
arXiv:2408.02689v3 Announce Type: replace-cross Abstract: Traffic forecasting uses recent measurements by sensors installed at chosen locations to forecast the future road traffic. Existing work eithe
arXiv:2601.12310v2 Announce Type: replace Abstract: Self-training systems often degenerate due to the lack of an external criterion for judging data quality, leading to reward hacking and semantic dri
arXiv:2609.39019v1 Announce Type: new Abstract: Multi-view learning seeks to learn more comprehensive representations by exploiting the complementarity and consistency across diverse modalities or vie
arXiv:2609.38653v1 Announce Type: cross Abstract: Recent advances in musculoskeletal modeling and reinforcement learning have enabled muscle-actuated agents to reproduce increasingly complex human mot
arXiv:2609.39343v1 Announce Type: new Abstract: Diffusion caching accelerates generation by replacing transformer computation with cached or predicted features at selected denoising steps. We introduc
arXiv:2609.40083v1 Announce Type: cross Abstract: One-class artifact detectors for whole-slide images learn normal tissue from a clean training pool and flag departures from it. The pool is built by a
arXiv:2609.38395v1 Announce Type: cross Abstract: Stochastic differential equations (SDEs) can be studied via Ito calculus and rough path theory. For stochastic optimal control, these two frameworks g
arXiv:2607.18446v2 Announce Type: replace Abstract: Purpose: Understanding how much of routine policing involves vulnerable people could inform resourcing, training, and multi-agency response, yet adm
arXiv:2609.38887v1 Announce Type: cross Abstract: Real-time voice conversion (VC) systems commonly rely on pretrained speaker embeddings from automatic speaker verification (ASV) models. While effecti
arXiv:2609.39989v1 Announce Type: new Abstract: Background. A component replacement in a language-model agent changes an execution trajectory, potentially altering later observations, resource use, an
arXiv:2609.38446v1 Announce Type: cross Abstract: A reward can identify a correct answer while leaving the computation needed for new inputs undetermined. We study how pretraining and midtraining supp
arXiv:2609.39232v1 Announce Type: cross Abstract: EDF relies on continuous monitoring of its power plants to detect anomalies as soon as they occur. Given the absence of a universally optimal streamin
arXiv:2609.38995v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a student on its own generated responses using feedback from the same model conditioned on privileged informat
arXiv:2609.38818v1 Announce Type: new Abstract: Organizations increasingly route employee feedback to leaders through large language model (LLM) summaries, an unaudited layer that silences already-spo
arXiv:2609.37649v1 Announce Type: cross Abstract: Many datasets carry an intrinsic directionality: citations point backward in time, cells differentiate along lineages, and traffic follows preferred r
arXiv:2609.37857v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly scaled to wider dictionaries to recover fine-grained structure from large language model activations. Howeve
arXiv:2606.16996v2 Announce Type: replace-cross Abstract: Segment Anything Model 3 (SAM 3) provides a strong frozen backbone for concept-prompted segmentation, but applying it directly to open-vocabul
arXiv:2609.36119v1 Announce Type: new Abstract: Spatial-temporal (ST) forecasting underpins many real-world systems such as traffic, climate, and energy networks. While existing methods implicitly ass
arXiv:2609.32472v2 Announce Type: replace Abstract: Document rerankers determine what evidence reaches the downstream model in RAG and deep research, yet mainstream rerankers select by relevance match
arXiv:2509.20411v3 Announce Type: replace-cross Abstract: Machine learning-based cybersecurity systems are highly vulnerable to adversarial attacks, while Generative Adversarial Networks (GANs) act as
arXiv:2609.36563v1 Announce Type: new Abstract: Visual emotion recognition commonly assumes that all evidence required for prediction is contained in the observed image or video. Yet the same visible
arXiv:2609.35914v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it suitable for privacy-sensi
arXiv:2609.36662v1 Announce Type: cross Abstract: The pre-training of Large Language Models (LLMs) is increasingly conducted across multiple data centers. As training scales to a larger number of acce
arXiv:2609.37263v1 Announce Type: new Abstract: While Large Vision-Language Models (LVLMs) achieve remarkable success, hallucinations remain a significant barrier to their reliable deployment. Recent
arXiv:2609.35856v1 Announce Type: cross Abstract: This research describes the adaptation of Large Language Models (LLMs) for economic monitoring in the public sector to automatically determine whether
arXiv:2609.36168v1 Announce Type: new Abstract: Depth completion aims to recover dense metric depth from sparse sensor measurements, increasingly leveraging visual foundation models as geometric prior
arXiv:2609.37097v1 Announce Type: new Abstract: The rapid growth of submissions and reviewing workload has accelerated the use of large language models (LLMs) in peer review. Prior studies suggest tha
arXiv:2609.36505v1 Announce Type: new Abstract: Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by
arXiv:2609.36806v1 Announce Type: new Abstract: Modern engineering systems, from automobiles to aircraft, are designed by using precise, continuous parametric computer-aided design (CAD) models. Evalu
arXiv:2609.36400v1 Announce Type: cross Abstract: Deep learning classifiers for dermoscopic skin lesions often reach high in-distribution accuracy while quietly relying on spurious background cues suc
arXiv:2609.35821v1 Announce Type: new Abstract: Disaster social sensing converts public social-media posts into evidence for situational awareness and humanitarian needs, but generative artificial int
arXiv:2609.36024v1 Announce Type: new Abstract: Reconstructing simulation-ready 3D scenes from real-world observations enables robotics, gaming, and immersive applications, yet existing methods largel
arXiv:2602.20731v2 Announce Type: replace-cross Abstract: Discrete image tokenizers provide a sequential interface for vision and multimodal models, but are typically optimized for reconstruction or c
arXiv:2609.38087v1 Announce Type: new Abstract: Behavior Foundation Models (BFMs) give humanoids a promptable policy over a latent behavior space, enabling one single vector to represent a motion to i
arXiv:2609.36782v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) have demonstrated exceptional capabilities in objective understanding tasks, their performance in affecti
arXiv:2609.36812v1 Announce Type: cross Abstract: Diffusion and flow policies can model complex behaviors in offline reinforcement learning (RL). However, penalizing their KL divergence from the behav
arXiv:2609.36482v1 Announce Type: new Abstract: Quadrotor racing demands aggressive attitude and progress control while passing through every gate, and conventional quadrotor MPCC formulations state t
arXiv:2609.38099v1 Announce Type: cross Abstract: Turning decoder-only large language models (LLMs) into strong dense retrievers typically requires some form of retriever training. In this paper, we a
arXiv:2501.18157v2 Announce Type: replace-cross Abstract: Building reliable speech systems often requires combining multiple modalities, like audio and visual cues. While such multimodal solutions fre
arXiv:2609.36460v1 Announce Type: cross Abstract: Several tonal pitch spaces and computational models have been proposed to analyze tonal structure in Western tonal music, many of them grounded in pri