Knowledge catalogue
arXiv:2607.28408v1 Announce Type: new Abstract: This thesis studies policy learning in interactive systems where an agent observes a context, selects an action from a very large set, and receives part
arXiv:2607.27475v1 Announce Type: cross Abstract: In modern recommendation systems, retrieval serves as a primary stage responsible for filtering billions of candidate items down to thousands prior to
arXiv:2607.28154v1 Announce Type: new Abstract: Interleaved multimodal Chain-of-Thought (CoT) improves visual reasoning by incorporating auxiliary visual evidence into intermediate reasoning. However,
arXiv:2607.18866v2 Announce Type: replace-cross Abstract: Building on the identity that expected regret equals the covariance between costs and decisions, this paper develops a derivative theory of th
arXiv:2607.27574v1 Announce Type: new Abstract: Activation steering has emerged in large language models as a lightweight alternative for dynamically changing a model's behavior at inference time. How
arXiv:2506.21076v4 Announce Type: replace Abstract: Pose stylization, which aims to synthesize stylized content aligning with target poses, serves as a fundamental task across 2D, 3D, and video domain
arXiv:2601.10600v2 Announce Type: replace-cross Abstract: In the context of multi-agent multi-armed bandits (MA-MAB), fairness is often reduced to outcomes: maximizing welfare, reducing inequality, or
arXiv:2607.28415v1 Announce Type: cross Abstract: Latent world models enable efficient planning by predicting future states in a compact representation space, but their performance depends critically
arXiv:2607.27568v1 Announce Type: new Abstract: Recognition accuracy obtained during a recording session does not persist when a user puts on the electrodes again after the electrodes had previously b
arXiv:2607.27631v1 Announce Type: cross Abstract: Reinforcement learning has emerged as an effective paradigm for enhancing the mathematical reasoning capabilities of large language models. Among exis
arXiv:2603.13707v3 Announce Type: replace-cross Abstract: Humanoid loco-manipulation requires coordinated task-space motion planning with stable loco-manipulation command tracking under complex robot-
arXiv:2607.27260v1 Announce Type: new Abstract: Multimodal continual learning (MMCL) aims to learn emerging knowledge from multimodal data while preserving knowledge. To mitigate forgetting, current M
arXiv:2607.27209v1 Announce Type: cross Abstract: Peer review at ML conferences increasingly relies on reviewer scores as the primary decision instrument. As submissions have scaled from thousands to
arXiv:2607.28581v1 Announce Type: new Abstract: High-fidelity 3D generation predominantly relies on scaling model capacity and data, which incurs prohibitive computational costs. This paradigm typical
arXiv:2607.27815v1 Announce Type: cross Abstract: Local differential privacy (LDP) protocols are vulnerable to poisoning attacks. Existing research have proposed efficient defense strategies for singl
arXiv:2607.28488v1 Announce Type: cross Abstract: Can supply-chain AI move beyond isolated decision modules toward unified operational planning? A complete replenishment plan specifies which products
arXiv:2607.26566v1 Announce Type: cross Abstract: Text-to-image (T2I) workflows are increasingly deployed on serverless platforms because users often compose customized workflows and invoke them inter
arXiv:2607.26070v1 Announce Type: cross Abstract: Large language model (LLM)-based agentic search systems are often evaluated as if the underlying LLM were the only component that matters, yet their m
arXiv:2607.18785v2 Announce Type: replace Abstract: As large language model agents gain access to increasingly large skill libraries, retrieving the right skill becomes critical to reliable capability
arXiv:2607.27890v1 Announce Type: new Abstract: Visuomotor policies have advanced on manipulation tasks where the target object stays static during execution, but real deployments break this assumptio
arXiv:2607.27563v1 Announce Type: new Abstract: New venture start-ups need to ``survive'' through multiple stages of reaching milestone targets. We investigate the strategies for start-ups in a milest
arXiv:2607.28457v1 Announce Type: cross Abstract: Scaling test-time computation can improve language-model reasoning, but uniform budgets waste computation on easy inputs, while verifier-guided refine
arXiv:2607.27973v1 Announce Type: new Abstract: Recently, Reinforcement Learning (RL) has emerged as a crucial paradigm for the post-training of Large Language Model (LLM) agents. However, existing me
arXiv:2607.28058v1 Announce Type: new Abstract: Recent advances in preference alignment for diffusion-based video generation, particularly via Direct Preference Optimization (DPO), have significantly
arXiv:2602.08159v2 Announce Type: replace-cross Abstract: When a language model asserts that 'the capital of Australia is Sydney,' does it know this is wrong? Models assert misconceptions with the sam
arXiv:2607.26067v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for estimating item difficulty in educational assessment. However, it remains unclear whether such
arXiv:2607.27281v1 Announce Type: new Abstract: A capability appears in a language model when the last parts of its circuit align in one stochastic attempt, and getting all but one right is worth noth
this is the whole problem in a nutshell. LLM-centered systems just can’t be trusted to follow hard constraints, we absolutely must find alternatives that can, or we are screwed. Anybody remember this
arXiv:2607.28198v1 Announce Type: cross Abstract: Many dexterous manipulation tasks require the object to remain securely held throughout the interaction. From the perspective of hand-object relationa
arXiv:2607.27897v1 Announce Type: new Abstract: Vision-language models (VLMs), such as CLIP, are vulnerable to adversarial attacks, posing a serious problem for real-life applications and deployment.
arXiv:2607.28590v1 Announce Type: cross Abstract: Multimodal on-policy distillation (OPD) transfers fine-grained visual knowledge by supervising student-generated trajectories with a privileged-view t
arXiv:2511.23310v3 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective paradigm for post-training large language models, yet the de
arXiv:2607.27530v1 Announce Type: new Abstract: Graph-text retrieval typically maps a graph and its description to a single embedding, even when a query concerns only one semantic aspect, such as a cl
arXiv:2607.27599v1 Announce Type: cross Abstract: Building generalizable agents for diverse applications remains a fundamental challenge. While imitation learning-based policies succeed in specific tr
arXiv:2607.26545v1 Announce Type: cross Abstract: We propose an index for predicting the U.S. Federal Open Market Committee (FOMC) decision to hike/hold/cut the current federal funds target rate based
arXiv:2607.26533v1 Announce Type: new Abstract: Graph Foundation Models (GFMs) aim to learn transferable knowledge from multi-domain graphs and adapt to unseen scenarios. As a fundamental source of re
arXiv:2607.26998v1 Announce Type: cross Abstract: Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by
Database security traditionally relies on a fragile balance between the granular control developers need and the administrative overhead of managing thousands of individual database passwords. Between
arXiv:2607.27154v1 Announce Type: new Abstract: CT vision-language foundation models have demonstrated promising performance across downstream tasks, but are typically trained with whole-volume repres
arXiv:2607.26647v1 Announce Type: new Abstract: While text-to-image diffusion models achieve impressive visual quality, they frequently struggle to maintain precise alignment with complex compositiona
arXiv:2607.26729v1 Announce Type: new Abstract: Deep learning-based watermarking has shown strong robustness against non-geometric distortions, yet its performance under geometric transformations rema
arXiv:2607.26452v1 Announce Type: cross Abstract: World models must learn the joint dynamics of states, actions, events, and observations, yet existing video, robotics, and simulation datasets usually
arXiv:2607.26789v1 Announce Type: new Abstract: Vision-language-action (VLA) policies commonly execute long-horizon mobile manipulation through open-loop action chunks, issuing multiple actions withou
arXiv:2607.26200v1 Announce Type: new Abstract: Content-moderation classifiers are usually evaluated in isolation, but deployment requires choosing where to intervene and what follows a flag. We evalu
arXiv:2607.26529v1 Announce Type: new Abstract: Cinematic video generation is challenging for text-to-video diffusion models due to concurrent requirements on multi-shot generation, fine-grained contr
arXiv:2607.26509v1 Announce Type: new Abstract: Deep off-policy reinforcement learning algorithms for continuous control typically rely on neural value function approximation to guide policy improveme
arXiv:2607.26164v1 Announce Type: new Abstract: Automated molecular structure elucidation from infrared (IR) spectroscopy data has seen significant advancements in recent years, but its broad applicab
arXiv:2607.26891v1 Announce Type: new Abstract: Sequence labeling is a fine-grained information extraction task, yet existing large language model-based approaches suffer from insufficient domain alig
arXiv:2607.26811v1 Announce Type: new Abstract: Existing autoregressive video distillation methods commonly adopt a Distribution Matching Distillation (DMD)-based multi-stage pipeline. However, they t
arXiv:2607.26066v1 Announce Type: new Abstract: The growing volume of scientific submissions has motivated interest in using large language models (LLMs) to assist peer review. Existing automated nove
arXiv:2607.26411v1 Announce Type: new Abstract: Unified multimodal models (UMMs) aim to integrate understanding and generation within a single architecture, yet it remains unclear whether these capabi
arXiv:2607.27203v1 Announce Type: new Abstract: Pre-training followed by fine-tuning has become the dominant recipe for learning performant policies, and in value-based reinforcement learning (RL) thi
arXiv:2607.26735v1 Announce Type: new Abstract: Prompt inversion, as a typical reverse engineering technique, enables text-to-image (T2I) diffusion models to generate the desired target images without
arXiv:2607.26253v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all resp
arXiv:2607.26292v1 Announce Type: new Abstract: Diffusion MRI (dMRI) relies on diffusion-weighted echo-planar imaging, which is highly susceptible to eddy-current-induced geometric distortions. These
arXiv:2607.27022v1 Announce Type: new Abstract: Regional bias in large language models (LLMs) may shape both perceptions of regional groups and decisions about individuals from different regions. Yet
arXiv:2607.26645v1 Announce Type: new Abstract: Existing point-based generative methods for outdoor scenes primarily focus on LiDAR-conditioned completion. During training, noisy point clouds are cons
arXiv:2607.26825v1 Announce Type: new Abstract: Large language models (LLMs) encode rich concept-like information, but represent it implicitly through distributed statistical associations rather than
arXiv:2607.26521v1 Announce Type: new Abstract: Conventional subgroup analyses can yield unstable and difficult-to-interpret conclusions, especially in observational biomedical data where each individ
arXiv:2604.05175v2 Announce Type: replace-cross Abstract: We consider constrained ergodic resource optimization in wireless networks with graph-structured interference. We train a diffusion model poli