Knowledge catalogue
arXiv:2609.36652v1 Announce Type: new Abstract: Open-ended generation lacks canonical answers, making pointwise rewards difficult to calibrate for group-based reinforcement learning. Directly ranking
arXiv:2609.35549v2 Announce Type: replace Abstract: Rare-disease diagnosis is a long-tail reasoning problem: phenotypes are incomplete, individual disorders are sparsely documented, and relevant evide
arXiv:2609.37588v1 Announce Type: new Abstract: Users of language-based assistive agents often make ambiguous requests. In response, an assistant can either directly act on its interpretation of the r
arXiv:2603.17815v2 Announce Type: replace Abstract: Understanding and evaluating multi-step reasoning in LLMs at the level of individual steps remains a key challenge. Process reward models (PRMs) pro
arXiv:2609.37530v1 Announce Type: cross Abstract: Vision-language-action (VLA) models typically operate on RGB images produced by a fixed camera image signal processor (ISP), leaving the imaging pipel
arXiv:2609.37015v1 Announce Type: new Abstract: We propose RBF-GNN, a new pseudo-coordinate based graph neural network architecture that takes into account Euclidean, spherical or angular coordinates
arXiv:2609.36540v1 Announce Type: new Abstract: Generalist robot policies such as vision-language-action models (VLAs) have achieved remarkable generalization, but their inference delays can conflict
arXiv:2609.37688v1 Announce Type: new Abstract: Reading behaviour varies not only with linguistic input, but also with reader proficiency. In this study, we investigate whether the layer-wise relation
arXiv:2609.37089v1 Announce Type: new Abstract: Real-world videos provide rich demonstrations of manipulation, but turning them into reusable robot skills requires visually aligned environments, execu
arXiv:2609.36984v1 Announce Type: new Abstract: Complex questions often require multi-hop reasoning that connects facts distributed across sources or distant regions of a long context through intermed
arXiv:2609.35694v2 Announce Type: replace Abstract: Continuous diffusion generates complete reasoning solutions through iterative refinement in latent space. We introduce the Continuous Embedding Diff
arXiv:2609.36126v1 Announce Type: cross Abstract: Modern AI architectures used to solve visual reasoning tasks typically rely heavily on global connectivity and synchronization. As biological systems
arXiv:2609.37889v1 Announce Type: new Abstract: Multimodal continual instruction tuning (MCIT) aims to enable multimodal large language models to acquire new capabilities from sequential tasks while p
arXiv:2609.37831v1 Announce Type: new Abstract: Real-time diffusion-based video super-resolution (VSR) is in high demand for online streaming, yet stringent latency requirements often compromise gener
arXiv:2609.36391v1 Announce Type: cross Abstract: An ongoing challenge in sensory neuroscience is to characterize the feature dimensions encoded by cortical populations. Recent approaches probe featur
arXiv:2609.38112v1 Announce Type: cross Abstract: Many applications of black-box predictive models require controlling task-relevant error rates, such as missed lesion pixels in segmentation or missed
arXiv:2501.03598v2 Announce Type: replace-cross Abstract: Knowledge graphs have proven successful in integrating heterogeneous data across various domains. However, there remains a noticeable dearth o
arXiv:2609.37734v1 Announce Type: new Abstract: Research in modular robotics has produced capable approaches allowing a robot's morphology to change online, with recent efforts also developing approac
arXiv:2609.35900v1 Announce Type: cross Abstract: The integration of large language models (LLMs) into scientific workflows is accelerating, yet their ability to reconstruct the reasoning underlying p
arXiv:2609.36737v1 Announce Type: cross Abstract: The vocal tract is the region of the human body responsible for filtering one's voice to create speech. In this paper, we present a differentiable and
arXiv:2609.37292v1 Announce Type: new Abstract: Physical active vision allows robots to change their viewpoint when task-relevant observations become unreliable, yet existing manipulation benchmarks p
arXiv:2609.36822v1 Announce Type: new Abstract: The rapid evolution of image generators calls for forensic cues that generalize beyond known generation mechanisms. Existing detectors often rely on sta
arXiv:2609.36329v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) determines not only how many parameters are trained, but also which local directions a model can move in, so simi
arXiv:2609.37131v1 Announce Type: new Abstract: Human-in-the-loop reinforcement learning (HIL-RL) offers a promising route to efficient training of robotic manipulation policies by combining autonomou
arXiv:2603.11210v2 Announce Type: replace Abstract: Machine unlearning aims to remove the influence of specific training data from a model while preserving its general utility. In vision, many approxi
arXiv:2609.37491v1 Announce Type: cross Abstract: Retrieval-augmented language models are expected to answer from the retrieved evidence, but in practice they often keep answering when that evidence i
arXiv:2609.36496v1 Announce Type: new Abstract: Most video editing methods focus on changing the appearance of the source video, while offering limited control over its dynamics. We introduce Reimagin
arXiv:2609.37850v1 Announce Type: new Abstract: Large generative models can recover realistic detail in real-world video super-resolution (VSR), but processing an entire video with them is computation
arXiv:2609.37469v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) grounds large language models in external sources, but retrieved passages often name the right entities without pro
arXiv:2609.36525v1 Announce Type: cross Abstract: Distributed inference has become an indispensable part of deploying medical models under practical latency, memory, and throughput constraints. Althou
arXiv:2609.35824v1 Announce Type: new Abstract: Large language models (LLMs) can give reliable labels under one setup yet change those labels when researchers make other reasonable design choices. We
arXiv:2609.36452v1 Announce Type: cross Abstract: Masked diffusion language models (MDLMs) can generate text efficiently by predicting multiple masked tokens in parallel, but predictions from the same
arXiv:2609.32965v2 Announce Type: replace Abstract: Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a repository, but another continues to
arXiv:2609.37587v1 Announce Type: cross Abstract: Longitudinal electronic health record (EHR) modeling requires integrating new visits with an expanding patient history. Yet the continual accumulation
arXiv:2609.35867v1 Announce Type: new Abstract: We propose ReLOBGen, a method for generating limit order book (LOB) messages that are replayable by construction. Replayability is required for closed-l
arXiv:2609.37311v1 Announce Type: new Abstract: Recent Recommendation Agents (RecAgents) offer a promising alternative by shifting recommendation to an active, user-side paradigm, where generative age
arXiv:2609.37307v1 Announce Type: new Abstract: Vision-language-action (VLA) models have driven rapid progress in robotic manipulation, demonstrating strong fine-grained control and promising performa
arXiv:2609.36121v1 Announce Type: cross Abstract: Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior. In this paper
arXiv:2609.36974v1 Announce Type: new Abstract: Text-to-speech models loop, truncate and lose count on text that repeats a phrase many times. We show that repetition itself is what breaks them, not th
arXiv:2609.36654v1 Announce Type: cross Abstract: Large language models make weight storage and memory traffic major inference costs, motivating low-precision formats that represent each weight with o
arXiv:2609.35917v1 Announce Type: new Abstract: Graph neural networks are increasingly applied to road-level crash prediction, but the stability of their reported gains has received little scrutiny. W
arXiv:2609.32490v2 Announce Type: replace Abstract: LLM-based multi-agent systems (MASs) have shown strong potential for solving complex tasks, but most assume that task requirements are sufficiently
arXiv:2609.36208v1 Announce Type: cross Abstract: Input encodings can restrict which measured contrasts a predictor can jointly reproduce, even when no single contrast is forced to vanish. We compute
arXiv:2609.36348v1 Announce Type: cross Abstract: Generative and representation learning remain asymmetrically connected: semantic representations are used to improve diffusion generation, whereas the
arXiv:2609.36916v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) incur high inference latency from long visual token sequences. Existing pruning methods commonly use attention
arXiv:2609.36288v1 Announce Type: new Abstract: EEG foundation models (EEG-FMs) are intended to generalize across different datasets by learning representations that, ideally, are invariant to dataset
arXiv:2609.35890v1 Announce Type: new Abstract: Sparse-autoencoder decomposability and concentrated feature attribution are increasingly treated as evidence that a model's computation is easier to rev
arXiv:2609.36680v1 Announce Type: new Abstract: Visual reprogramming adapts pretrained models to downstream tasks by modifying their input and output interfaces while keeping the backbone fixed. In vi
arXiv:2609.37225v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential for universal multimodal representation learning. However, existing methods eithe
arXiv:2609.36813v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational circuits. Howe
arXiv:2609.35864v1 Announce Type: new Abstract: SEC 10-K filings contain substantial financial information that is not consistently captured in structured datasets, creating a missing-data problem aff
arXiv:2609.36850v1 Announce Type: new Abstract: Generative content is increasingly entering the production and dissemination of news, transforming fake news from manually fabricated or simply manipula
arXiv:2609.36461v1 Announce Type: new Abstract: Large language models often improve problem-solving performance by generating multi-step reasoning paths, yet how to analyze the hidden states along the
arXiv:2609.38163v1 Announce Type: new Abstract: World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and predi
arXiv:2609.37391v1 Announce Type: new Abstract: Diffusion language models (DLMs) enable parallel generation by predicting and committing multiple tokens at each denoising step, yet they can generate i
arXiv:2609.38024v1 Announce Type: new Abstract: An agent skill is a reusable, actionable natural-language artifact that guides an agent to perform a task effectively under a given harness. Recent stud
arXiv:2609.37879v1 Announce Type: new Abstract: How many tokens from its context does a language model actually use, and what determines that number? We study this question through self-attention. Wit
arXiv:2609.36534v1 Announce Type: new Abstract: Dense retrievers decide which documents reach users and the language models that use them, yet they are typically evaluated with neutral queries. We ask
arXiv:2609.37669v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is increasingly used to enhance Large Language Model (LLM)-based software vulnerability detection by grounding pr
arXiv:2511.11164v3 Announce Type: replace Abstract: Bridging the past to the future, connecting agents both spatially and temporally, lies at the core of the trajectory prediction task. Despite great