Knowledge catalogue
arXiv:2605.12264v1 Announce Type: cross Abstract: Supervised Finetuning (SFT) has become one of the primary methods for adapting a large language model (LLM) with extensive pre-trained knowledge to do
arXiv:2605.11502v1 Announce Type: new Abstract: Accurately and consistently indexing biomedical literature by publication type and study design is essential for supporting evidence synthesis and knowl
arXiv:2605.11680v1 Announce Type: new Abstract: We introduce ShapeCodeBench, a synthetic benchmark for perception-to-program reconstruction: given a rendered raster image, a model must emit an executa
arXiv:2605.12456v1 Announce Type: cross Abstract: We introduce TextSeal, a state-of-the-art watermark for large language models. Building on Gumbel-max sampling, TextSeal introduces dual-key generatio
arXiv:2605.12452v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate fluent political text at scale, raising concerns about synthetic discourse during crises and social conflict.
arXiv:2507.13841v2 Announce Type: replace Abstract: Good storytelling involves surprise -- unpredictability in how the story unfolds -- and sense-making, the requirement that the story forms a coheren
arXiv:2503.16072v4 Announce Type: replace-cross Abstract: Toxicity detection has become core safety infrastructure for online moderation, dataset filtering, and deployed language-model systems. Yet mo
arXiv:2605.11551v1 Announce Type: cross Abstract: Detecting out-of-distribution (OOD) samples is critical for safe deployment of neural networks in safety-critical applications. While maximum softmax
arXiv:2605.10256v1 Announce Type: cross Abstract: Most recent advances in audio dereverberation focus almost exclusively on speech, leaving percussive and drum signals largely unexplored despite their
arXiv:2602.06457v2 Announce Type: replace Abstract: Online bilevel optimization (OBO) has emerged as a powerful framework for many machine learning problems. Prior works have developed several algorit
arXiv:2605.10286v1 Announce Type: new Abstract: Building effective clinical decision support systems requires the synthesis of complex heterogeneous multimodal data. Such modalities include temporal e
arXiv:2605.08480v1 Announce Type: new Abstract: Individuals with Alzheimer's disease (AD) and Alzheimer's disease-related dementia (ADRD) experience memory and thinking changes that impact their abili
arXiv:2601.01762v2 Announce Type: replace-cross Abstract: Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. W
arXiv:2603.26680v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) evolve into lifelong AI assistants, LLM personalization has become a critical frontier. However, progress is c
arXiv:2512.15977v3 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly proposed as general-purpose solutions for visual recognition tasks, yet their reliability for agricul
arXiv:2605.08354v1 Announce Type: new Abstract: Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human
arXiv:2605.10370v1 Announce Type: new Abstract: Scientific knowledge on the Web is published as passive assertions and cannot decide when to validate evidence, reconcile contradictions, or update conf
arXiv:2605.10845v1 Announce Type: cross Abstract: As global cross-lingual communication intensifies, language barriers in visually rich documents such as PDFs remain a practical bottleneck. Existing d
arXiv:2605.10865v1 Announce Type: new Abstract: Industrial Computer-Aided Design (CAD) code generation requires models to produce executable parametric programs from visual or textual inputs. Beyond r
arXiv:2605.08296v1 Announce Type: new Abstract: Human Activity Recognition (HAR) from wearable sensors supports broad healthcare and behavior science applications. However, data heterogeneity and the
arXiv:2605.08136v1 Announce Type: cross Abstract: Visual perception plays a central role in competitive robotics, where environmental variations can directly affect real-time detection performance. Th
arXiv:2605.10438v1 Announce Type: cross Abstract: Current 3D tokenizers largely treat representation as spatial compression: compact codes reconstruct surface geometry, but leave component ownership a
arXiv:2605.09611v1 Announce Type: new Abstract: This preprint presents an empirical analysis of byte-exact chunk-level deduplication in Retrieval-Augmented Generation (RAG) pipelines. We measure conte
arXiv:2605.10744v1 Announce Type: new Abstract: Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing
arXiv:2605.10873v1 Announce Type: cross Abstract: Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existin
arXiv:2605.08439v1 Announce Type: new Abstract: Accurately communicating the side effects of cancer treatments to cancer survivors is critical, particularly in settings such as informed consent, where
arXiv:2605.08556v1 Announce Type: new Abstract: LLMs are increasingly used to make or support high-stakes decisions under uncertainty, where alignment depends not only on factual accuracy but on how m
arXiv:2605.08493v1 Announce Type: new Abstract: Wireless capsule endoscopy (WCE) enables non-invasive visual assessment of the small bowel, but its clinical utility is constrained by the large volume
arXiv:2605.08590v1 Announce Type: cross Abstract: LLMs are increasingly used to explain personal sensing data, translating traces of activity and mood into natural-language accounts of why an anomalou
arXiv:2603.28902v2 Announce Type: replace Abstract: Charts are central to analytical reasoning, yet existing benchmarks for chart understanding focus almost exclusively on single-chart interpretation
arXiv:2605.10840v1 Announce Type: cross Abstract: We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architec
arXiv:2605.09584v1 Announce Type: cross Abstract: Inpatient clinical reasoning is a sequential decision under partial observability: the clinician sees the admission so far and must choose the next ac
arXiv:2601.16836v3 Announce Type: replace-cross Abstract: Text-to-image (T2I) models have advanced considerably in generating high-quality images from textual descriptions. However, their ability to a
arXiv:2605.08681v1 Announce Type: cross Abstract: We study solving large-scale fixed-point equation (x^star=ar F(x^star)) with decomposition. Standard strict decomposition assigns each agent a disjoin
arXiv:2605.10894v1 Announce Type: new Abstract: Deep learning models in medical imaging often fail when deployed in new clinical environments due to distribution shifts in demographics, scanner hardwa
arXiv:2605.10597v1 Announce Type: cross Abstract: Benchmarks for coding agents increasingly measure source-level software repair, and cybersecurity benchmarks increasingly measure broad capture-the-fl
arXiv:2603.09970v2 Announce Type: replace Abstract: A key component of creativity is associative reasoning: the ability to draw novel yet meaningful connections between concepts. We introduce CREATE,
arXiv:2605.08467v1 Announce Type: new Abstract: Large language models show promise for automated CUDA programming, however even the strongest coding models (e.g., Claude-Opus-4.6) may still fall short
arXiv:2605.10166v1 Announce Type: new Abstract: Robotic imitation learning typically assumes access to optimal demonstrations, yet real-world data collection often yields suboptimal, exploratory, or e
arXiv:2605.10906v1 Announce Type: cross Abstract: As model families, training recipes, and compute budgets become increasingly standardized, further gains in machine learning systems depend increasing
arXiv:2604.01151v2 Announce Type: replace Abstract: As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human o
arXiv:2507.01008v3 Announce Type: replace Abstract: Development of dexterous manipulation hardware has primarily focused on hands and grippers. However, these end-effectors are often paired with bulky
arXiv:2605.09697v1 Announce Type: new Abstract: In many real-world computer vision applications, including medical imaging and industrial inspection, binary classification tasks are characterized by a
arXiv:2605.09391v1 Announce Type: new Abstract: It is becoming increasingly necessary to have monitors check for harmful behaviors during language model interactions, but text-only monitoring has not
arXiv:2605.10281v1 Announce Type: cross Abstract: Generating realistic drum audio directly from symbolic representations is a challenging task at the intersection of music perception and machine learn
arXiv:2605.10770v1 Announce Type: new Abstract: Multi-domain fine-tuning of large language models requires improving performance on target domains while preserving performance on constrained domains,
arXiv:2605.10261v1 Announce Type: new Abstract: TCAV (Testing with Concept Activation Vectors) is an interpretability method that assesses the alignment between the internal representations of a train
arXiv:2510.19414v2 Announce Type: replace-cross Abstract: The growing prevalence of speech deepfakes has raised serious concerns, particularly in real-world scenarios such as telephone fraud and ident
arXiv:2605.09378v1 Announce Type: cross Abstract: Long-horizon video generation has advanced in visual quality, yet existing methods still struggle to maintain knowledge consistency and coherent pedag
arXiv:2603.09465v3 Announce Type: replace-cross Abstract: Vision-Language-Action models have shown great promise for autonomous driving, yet they suffer from degraded perception after unfreezing the v
arXiv:2605.10663v1 Announce Type: new Abstract: Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactio
arXiv:2605.08769v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems have shown strong potential on complex tasks through agent specialization, tool use, and collaborat
arXiv:2605.10343v1 Announce Type: cross Abstract: Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness ag
arXiv:2507.11185v2 Announce Type: replace-cross Abstract: Heart disease continues to pose a critical worldwide health issue, more specifically in areas with insufficient access to healthcare infrastru
arXiv:2509.13332v2 Announce Type: replace Abstract: As Large Language Models (LLMs) are increasingly adopted as automated judges in benchmarking and reward modeling, ensuring their reliability, effici
arXiv:2605.08398v1 Announce Type: cross Abstract: In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capaci
arXiv:2603.00166v2 Announce Type: replace-cross Abstract: Recent advances in generative AI have shown human-level performance in complex content creation. However, we identify a 'Paradox of Simplicity
arXiv:2605.08820v1 Announce Type: cross Abstract: Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to concrete real-world claims, creating new cha
arXiv:2605.09839v1 Announce Type: cross Abstract: We introduce the Free Energy Manifold (FEM), a score-trained conditional energy model specialized for inference in hybrid Bayesian networks with discr
arXiv:2605.08733v1 Announce Type: new Abstract: Expressive generative policies such as diffusion and flow models are appealing for MaxEnt online reinforcement learning because of their ability to mode