Knowledge catalogue
arXiv:2510.05408v2 Announce Type: replace Abstract: Recovering the past from present observations is an intriguing challenge with potential applications in forensics and scene analysis. Thermal imagin
arXiv:2509.00931v3 Announce Type: replace-cross Abstract: We present a novel deep generative semi-supervised framework for credit card fraud detection, formulated as time series classification task. A
arXiv:2605.12500v1 Announce Type: new Abstract: Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as disti
arXiv:2605.11547v1 Announce Type: new Abstract: Flow matching models generate samples by numerically integrating a learned velocity field, with each integration step requiring a neural network evaluat
arXiv:2605.12466v1 Announce Type: cross Abstract: Looped Transformers offer a promising alternative to purely feed-forward computation by iteratively refining latent representations, improving languag
arXiv:2605.11317v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in multi-turn dialogue settings where preserving conversational context across turns is essential
arXiv:2505.05772v2 Announce Type: replace Abstract: Transformer-based models are the foundation of modern machine learning, but their execution, particularly during autoregressive decoding in large la
arXiv:2603.24033v2 Announce Type: replace Abstract: We propose Score-based Relaxation-guided Generation (SRG), a generative framework based on an approximate formulation of relaxation-guided stochasti
arXiv:2605.11572v1 Announce Type: new Abstract: Audio-visual understanding requires effective alignment between heterogeneous modalities, yet cross-modal correspondence remains challenging when tempor
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:2605.11550v1 Announce Type: new Abstract: A plausible scene evolution depends on the maneuver being considered, while a good maneuver depends on how the scene may evolve. Existing World Action M
arXiv:2605.05922v2 Announce Type: replace Abstract: Recent advances in generative video models are increasingly driven by post-training and test-time scaling, both of which critically depend on the qu
Today we release Token Superposition Training (TST), a modification to the standard LLM pretraining loop that produces a 2-3× wall-clock speedup at matched FLOPs without changing the model architectur
arXiv:2605.11974v1 Announce Type: new Abstract: Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements. This unfairness lim
arXiv:2605.11170v1 Announce Type: new Abstract: Noise-based certified machine unlearning currently faces a hard ceiling: the noise magnitude required to certify unlearning typically destroys model uti
arXiv:2605.11258v1 Announce Type: cross Abstract: Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that c
arXiv:2605.11864v1 Announce Type: cross Abstract: Listwise reranking is a key yet computationally expensive component in vision-centric retrieval and multimodal retrieval-augmented generation (M-RAG)
arXiv:2605.11424v1 Announce Type: new Abstract: Gaussian Splatting has achieved remarkable progress in multi-view surface reconstruction, yet it exhibits notable degradation when only few views are av
arXiv:2605.11654v1 Announce Type: new Abstract: Cross-view geo-localization (CVGL), which matches an oblique drone view to a geo-referenced satellite tile, has emerged as a key alternative for autonom
arXiv:2605.11612v1 Announce Type: new Abstract: Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token lev
arXiv:2605.11696v1 Announce Type: new Abstract: Recent single-image relighting methods, powered by advanced generative models, have achieved impressive photorealism on synthetic benchmarks. However, t
arXiv:2605.11743v1 Announce Type: new Abstract: Learning latent representations that capture both semantic and spatial information is central to efficient spatio-semantic reasoning. However, many exis
arXiv:2605.09515v1 Announce Type: new Abstract: Large language models rely on multihead attention, but interactions among heads remain poorly understood. We apply the Game Theoretic Free Energy Princi
arXiv:2605.10044v1 Announce Type: cross Abstract: Action chunking emerged as a pivotal technique in imitation learning, enabling policies to predict cohesive action sequences rather than single action
arXiv:2605.08704v1 Announce Type: new Abstract: Multi-agent reasoning has shown promise for improving the problem-solving ability of large language models by allowing multiple agents to explore divers
arXiv:2605.08756v1 Announce Type: new Abstract: Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs). Recent works show t
arXiv:2605.10718v1 Announce Type: cross Abstract: Grey failures in the computing continuum produce ambiguous overlapping symptoms that existing approaches fail to diagnose reliably, either due to a la
arXiv:2605.09995v1 Announce Type: new Abstract: Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy
arXiv:2605.09407v1 Announce Type: new Abstract: Modern object detectors are static, fixed-depth networks optimized for a single operating point, requiring separate models for different deployment scen
arXiv:2603.10126v2 Announce Type: replace-cross Abstract: We propose a standalone autoregressive (AR) Action Expert that generates actions as a continuous causal sequence while conditioning on refresh
arXiv:2511.14045v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a core training stage in recent large language models (LLMs). Its reliance on
arXiv:2602.09534v2 Announce Type: replace Abstract: Realistic talking-head video generation is critical for virtual avatars, film production, and interactive systems. Current methods struggle with nua
arXiv:2605.08214v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) and speaker diarization in Bangla remain challenging due to long form recordings, diverse acoustic conditions, and
arXiv:2601.03042v4 Announce Type: replace Abstract: Reliable confidence is essential for trusting the outputs of LLMs, yet widely deployed post-trained LLMs (PoLLMs) typically compromise this trust wi
arXiv:2601.02950v3 Announce Type: replace Abstract: Current Large Language Model reasoning systems process queries independently, discarding valuable cross-instance signals such as shared reasoning pa
arXiv:2308.13222v3 Announce Type: replace-cross Abstract: We introduce an evidence-driven Bayesian formulation of physics-informed neural networks that enables automatic optimization of loss weights b
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:2605.08136v1 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:2605.08421v1 Announce Type: new Abstract: Visual Document Retrieval (VDR) models mostly rely on late interaction architectures, in which documents are represented by a set of local patch embeddi
arXiv:2605.09463v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks. However, their deployment in long-context scenarios faces h
arXiv:2605.09146v1 Announce Type: new Abstract: Humanoid Visual Search (HVS) requires agents to actively explore immersive 360^irc environments. While prior methods treat this as a monolithic task rel
arXiv:2605.09579v1 Announce Type: cross Abstract: Cardiovascular disease remains the leading cause of global mortality, yet scalable cardiac monitoring is hindered by the gap between diagnostic-rich E
arXiv:2511.21104v3 Announce Type: replace Abstract: Large language models can generate plausible code, but remain brittle for formal verification in proof assistants such as Lean. A central scalabilit
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:2605.08653v1 Announce Type: new Abstract: Accurate state-of-charge (SOC) estimation is critical for the safe and efficient operation of lithium-ion batteries in battery management systems (BMS).
arXiv:2605.08325v1 Announce Type: cross Abstract: Many vision datasets now provide segmentation masks in addition to annotated images to support a wide range of tasks. In this work, we propose Class A
arXiv:2603.05495v2 Announce Type: replace Abstract: To scale optimization and simulation, prior work has explored training machine-learning surrogates that map problem parameters to solutions inexpens
arXiv:2605.09846v1 Announce Type: cross Abstract: In new media art creation, the mapping between vision and hearing is often subjective. As a classic carrier of sound visualization, Chladni patterns h
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:2605.09858v1 Announce Type: new Abstract: Multi-Object Tracking (MOT) in dynamic environments relies on robust temporal reasoning to maintain consistent object identities over time. Transformer-
arXiv:2605.10510v1 Announce Type: cross Abstract: Biomedical knowledge graphs are increasingly large, dynamic, and multimodal, driven by rapid advances in biotechnology such as high-throughput sequenc
arXiv:2605.08399v1 Announce Type: new Abstract: Tool-augmented language models can extend small language models with external executable skills, but scaling the tool library creates a coupled challeng
arXiv:2605.08735v1 Announce Type: new Abstract: Recent 'Thinking with Video' approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reas
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:2605.10642v1 Announce Type: new Abstract: Pretrained diffusion models provide powerful learned priors, but in scientific sampling the target distribution often depends on physical context that i
arXiv:2605.09760v1 Announce Type: new Abstract: A reliable resume-job matching system helps a company find suitable candidates from a pool of resumes and helps a job seeker find relevant jobs from a l
arXiv:2510.06637v3 Announce Type: replace-cross Abstract: Despite advances in test-time scaling and diffusion finetuning, guidance for Auto-Regressive Diffusion Models (ARDMs) remains underexplored. W
arXiv:2605.08856v1 Announce Type: new Abstract: Autoregressive neural simulators now match classical solvers on short-horizon prediction of physical systems, yet their accuracy degrades rapidly when r
Cool idea from Nous Research. What if you could speed up long-context pretraining with a subquadratic wrapper that you remove before deployment? That is the idea behind Lighthouse Attention. The metho