Knowledge catalogue
arXiv:2608.30699v1 Announce Type: cross Abstract: Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to d
arXiv:2608.30753v1 Announce Type: cross Abstract: In large-scale e-commerce retrieval, dual-encoder retrievers are op- timized for contrastive similarity, whereas downstream rerankers capture finer-gr
arXiv:2608.30428v1 Announce Type: cross Abstract: Strategic deception by LLM and VLM agents has emerged as a central AI alignment and safety concern. Social-deduction games (where each player holds a
arXiv:2608.30695v1 Announce Type: new Abstract: Real-world time series often exhibit irregular sampling and extended temporal horizons, requiring models to capture continuous-time dynamics across arbi
arXiv:2510.09347v2 Announce Type: replace Abstract: Unlike Business-to-Consumer e-commerce platforms (e.g., Amazon), inexperienced individual sellers on Consumer-to-Consumer platforms (e.g., eBay) oft
arXiv:2608.30406v1 Announce Type: new Abstract: Goal-conditioned reinforcement learning struggles with long horizons when rewards are sparse. While a planner can provide subgoals to guide a low-level
arXiv:2608.27580v2 Announce Type: replace Abstract: Safety guardrails serve as the last line of defense against harmful inputs and outputs of large language models (LLMs), yet they are trained and eva
arXiv:2608.30902v1 Announce Type: new Abstract: Adapting large language models to user-specific preferences is often constrained by the cost of human annotation, making preference optimisation impract
arXiv:2608.30821v1 Announce Type: cross Abstract: Composable scene modeling aims to recover a real indoor scene as complete, editable object assets arranged as observed, giving robot simulation and em
arXiv:2608.29865v1 Announce Type: new Abstract: Manga visual question answering requires models to answer questions over panel-based visual narratives, where relevant evidence is distributed across or
arXiv:2608.31057v1 Announce Type: new Abstract: Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles an
arXiv:2608.29266v1 Announce Type: cross Abstract: Researchers increasingly treat LLM survey responses as a proxy for human cultural values. This includes projecting model outputs onto instruments like
arXiv:2608.30676v1 Announce Type: new Abstract: When medical AI systems hallucinate clinical reasoning, the consequences extend beyond incorrect answers: fabricated justifications that superficially r
arXiv:2608.28931v1 Announce Type: cross Abstract: Matching users to interest categories at scale is central to personalized shopping, but the task is challenging in large e-commerce platforms, where l
arXiv:2608.29623v1 Announce Type: cross Abstract: Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning.
arXiv:2608.30719v1 Announce Type: new Abstract: Productive dialogue alignment requires distinguishing surface coordination (acknowledgments and smooth task progression) from epistemic alignment (conve
arXiv:2608.29286v1 Announce Type: new Abstract: As Multimodal Large Language Models (MLLMs) evolve into sophisticated interactive assistants, their reliability depends not only on following instructio
arXiv:2608.30237v1 Announce Type: cross Abstract: General embodied agents should perceive, predict, act, evaluate, and improve within a unified system. World models have shown great promise in buildin
arXiv:2608.28674v1 Announce Type: new Abstract: Multi-exposure is an efficient way to capture real-world high-dynamic-range (HDR) scenes. However, HDR imaging suffers from severe ghosting artifacts in
arXiv:2608.30028v1 Announce Type: new Abstract: This paper introduces a family of multiclass linear Perceptron classifiers with a multiplicative margin mechanism (MMPerc), as an alternative to standar
arXiv:2503.00610v2 Announce Type: replace-cross Abstract: Understanding how people perceive urban environments is essential for inclusive planning, yet conventional surveys are costly and difficult to
arXiv:2608.31065v1 Announce Type: new Abstract: Surgical phase recognition is key to context-aware computer-assisted feedback in vitreoretinal procedures, yet the scarcity of synchronized multimodal i
arXiv:2603.02482v2 Announce Type: replace-cross Abstract: Safety evaluation of multimodal large language models requires tracking not only whether an attack succeeds, but also how the interaction unfo
arXiv:2608.28933v1 Announce Type: new Abstract: Stereo reconstruction is one of the last remaining Computer Vision tasks where all state-of-the-art methods employ a heavy architectural inductive bias.
@NJHagens Great summary of the fiasco: A detailed deconstruction of @dwarkesh_sp’s wildly popular but dangerously misleading account of the OpenAI Hugging Face incident: https://garymarcus.substack.co
arXiv:2608.30194v1 Announce Type: new Abstract: Diffusion models have recently advanced text-to-video (T2V) generation, yet they still struggle with fine-grained compositional alignment, such as attri
arXiv:2608.30944v1 Announce Type: new Abstract: In online retailing, when a product sells out, a retailer often sees only the units sold, not how many customers would have bought it had inventory been
arXiv:2608.29589v1 Announce Type: new Abstract: Text-to-image (T2I) safety guardrails fail to generalize equitably to non-standard dialects. Evaluating 23,080 paired prompts across five English dialec
arXiv:2608.29136v1 Announce Type: cross Abstract: We ask whether a model protects a user in the same way when that user speaks rather than types. Using a single distress vignette---a physical injury o
arXiv:2601.15436v3 Announce Type: replace Abstract: We propose a novel perspective for probing LLM sycophancy in a direct and neutral way, mitigating various forms of uncontrolled bias, noise, or mani
arXiv:2608.28905v1 Announce Type: new Abstract: Generative recommenders increasingly emit semantic IDs (SIDs): each item is a short sequence of hierarchical discrete codes from a residual quantizer, d
arXiv:2502.20325v3 Announce Type: replace-cross Abstract: Multi-rotor aerial autonomous vehicles (MAVs, more widely known as 'drones') have been generating increased interest in recent years due to th
arXiv:2608.30317v1 Announce Type: cross Abstract: Online dynamic origin-destination (OD) matrix estimation (DODE) calibrates time-dependent OD demand to reproduce observed link-flow trajectories. In o
arXiv:2608.30003v1 Announce Type: new Abstract: Prototypical part-based models provide explainable predictions by comparing input regions to learned prototypes. However, current approaches are burdene
arXiv:2509.25256v4 Announce Type: replace-cross Abstract: The systematic assessment of AI systems is increasingly vital as these technologies enter high-stakes domains. To address this, the EU's Artif
arXiv:2608.29097v1 Announce Type: cross Abstract: This paper studies the problem of proportionally fair clustering, where the goal is to select k ``centers'' from a metric space that fairly represent
arXiv:2608.30247v1 Announce Type: new Abstract: Recent unified open-vocabulary detection (OVD) supports heterogeneous prompts, including text queries, visual exemplars, and their combinations, but oft
arXiv:2603.19843v2 Announce Type: replace-cross Abstract: The ubiquity of multimedia content is reshaping online information spaces, particularly in social media environments. At the same time, search
arXiv:2603.14602v3 Announce Type: replace-cross Abstract: Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-spec
arXiv:2608.30528v1 Announce Type: new Abstract: Reinforcement learning (RL) is used to improve the reasoning abilities of LLMs, while training data span heterogeneous tasks. However, most RL post-trai
arXiv:2608.29061v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (GCRL) aims to learn policies for reaching diverse goals entirely from fixed trajectory data. Long-horiz
arXiv:2608.30378v1 Announce Type: cross Abstract: Direct vision-language-action policies generate continuous robot actions efficiently, but standard behavior cloning leaves two complementary gaps: the
arXiv:2603.10009v2 Announce Type: replace-cross Abstract: Despite their sophisticated general-purpose capabilities, Large Language Models (LLMs) often fail to align with diverse individual preferences
arXiv:2508.16013v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in politically sensitive contexts, raising concerns about their susceptibility to ideological
arXiv:2505.17537v2 Announce Type: replace Abstract: Large language models (LLMs) often produce incorrect answers with high confidence, yet the factors associated with such overconfidence remain insuff
arXiv:2608.30760v1 Announce Type: new Abstract: Recent studies have shown that multimodal large language models (MLLMs) can serve as embodied agents, translating language instructions and visual obser
arXiv:2608.29301v1 Announce Type: new Abstract: Predicting future organ dysfunction in Intensive Care Unit (ICU) patients is critical for early clinical intervention, yet existing machine learning app
arXiv:2608.28620v1 Announce Type: new Abstract: Preference elicitation is essential for aligning AI systems with human values. Prior approaches (e.g., for organ allocation) often ask stakeholders to c
arXiv:2608.30553v1 Announce Type: cross Abstract: Generative Retrieval (GR) has emerged as a promising paradigm by mapping queries directly to Semantic IDs (SIDs) with powerful representation capabili
arXiv:2608.30874v1 Announce Type: cross Abstract: This paper considers decentralized contingency MPC for multi-agent control under a state-only information pattern, with particular focus on limited se
Pure scaling of LLMs did actually hit a wall; neurosymbolic AI rescued it. AI didn’t hit a plateau; pure LLMs did — until people used harnesses and tools to complement their weaknesses. Which was alwa
arXiv:2608.29798v1 Announce Type: cross Abstract: The same Persona behavior can be beneficial in one context but harmful in another, causing static Persona elicitation to perform inconsistently across
arXiv:2608.29280v1 Announce Type: cross Abstract: Standard clothing asset generation---restoring forward-facing flat-lay garment images from diverse real-world contexts---holds immense commercial valu
arXiv:2608.30727v1 Announce Type: cross Abstract: Small-object detection under long-tailed data distributions is a fundamental yet challenging problem in multimedia. Railway Foreign Object Detection (
arXiv:2608.29109v1 Announce Type: new Abstract: Large language models often answer structurally unanswerable questions, such as computing cot(-540{eg}) or evaluating (1).startswith('1'), instead of ab
arXiv:2608.31077v1 Announce Type: new Abstract: Outcome-based reinforcement learning provides verified feedback for language-model agents, but assigns trajectory-level advantage uniformly to all decis
arXiv:2608.29458v1 Announce Type: cross Abstract: Sandbagging, in which a model deliberately underperforms on an evaluation despite retaining the underlying capability, threatens the safety evaluation
arXiv:2608.30162v1 Announce Type: new Abstract: We present a reinforcement-learning agent that solves symbolic equations step by step, covering both nonlinear closed equations (radicals, exponentials,
arXiv:2608.30946v1 Announce Type: new Abstract: Closed-loop human-AI systems generate high-dimensional behavioural trajectories whose collective dynamics remain obscure. Using 297,915 learners' adapti
arXiv:2608.30912v1 Announce Type: new Abstract: Artificial intelligence (AI) and natural language processing (NLP) are increasingly used to extract, integrate, and interpret biomedical knowledge relev