Knowledge catalogue
arXiv:2508.19982v5 Announce Type: replace Abstract: Diffusion language models (DLMs) have recently emerged as an alternative to autoregressive approaches, offering parallel sequence generation and fle
arXiv:2604.07213v1 Announce Type: new Abstract: High-dimensional data are often modeled as lying near a low-dimensional manifold. We study how to construct diffusion processes on this data manifold in
arXiv:2604.08084v1 Announce Type: new Abstract: Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inhere
arXiv:2604.06863v1 Announce Type: cross Abstract: Skin-toned emojis are crucial for fostering personal identity and social inclusion in online communication. As AI models, particularly Large Language
arXiv:2604.07166v1 Announce Type: cross Abstract: Although visual foundation models like DINOv2 provide state-of-the-art performance as feature extractors, their complex, high-dimensional representati
arXiv:2604.08074v1 Announce Type: new Abstract: Reliable and weather-robust perception systems are essential for safe autonomous driving and typically employ multi-modal sensor configurations to achie
arXiv:2604.07723v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation (OVSS) aims to segment arbitrary category regions in images using open-vocabulary prompts, necessitating that exis
arXiv:2511.22599v2 Announce Type: replace-cross Abstract: Deploying Large Language Model (LLM) services at the edge benefits latency-sensitive and privacy-aware applications. However, the stateless na
arXiv:2604.06491v1 Announce Type: cross Abstract: We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matchi
arXiv:2604.06250v1 Announce Type: cross Abstract: When asked to describe a molecular diagram, a Vision-Language Model correctly identifies ``a benzene ring with an -OH group.'' When asked to reason ab
arXiv:2504.17069v2 Announce Type: replace Abstract: Autoregressive (AR) image generators are becoming increasingly popular due to their ability to produce high-quality images and their scalability. Ty
arXiv:2604.06483v1 Announce Type: cross Abstract: Large language models that require multiple GPU cards to host are usually the most capable models. It is necessary to understand and steer these model
arXiv:2604.08284v1 Announce Type: new Abstract: Large language models store not only isolated facts but also rules that support reasoning across symbolic expressions, natural language explanations, an
arXiv:2604.06210v2 Announce Type: cross Abstract: As LLMs are globally deployed, aligning their cultural value orientations is critical for safety and user engagement. However, existing benchmarks fac
arXiv:2604.07622v1 Announce Type: new Abstract: Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its
arXiv:2412.08637v4 Announce Type: replace Abstract: Identifying the training data samples that most influence a generated image is a critical task in understanding diffusion models (DMs), yet existing
arXiv:2602.11635v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have achieved strong performance on perception-oriented tasks, yet their ability to perform mathematical sp
arXiv:2604.06871v1 Announce Type: cross Abstract: Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence length
arXiv:2604.04344v2 Announce Type: replace Abstract: We establish a computation-substrate-agnostic inference architecture in which domain is an explicit first-class computational parameter. This produc
arXiv:2604.06342v1 Announce Type: cross Abstract: Although tension between university curricula and industry expectations has existed in some form for decades, the rapid integration of generative AI (
arXiv:2506.04500v3 Announce Type: replace-cross Abstract: Recent advancements in large language models (LLMs) have spurred interest in robotic navigation that incorporates complex spatial, mathematica
arXiv:2402.02249v3 Announce Type: replace Abstract: We study how to best spend a budget of noisy labels to compare the accuracy of two binary classifiers. It's common practice to collect and aggregate
arXiv:2604.08369v1 Announce Type: cross Abstract: Inference-time compute scaling has emerged as a powerful technique for improving the reliability of large language model (LLM) agents, but existing me
arXiv:2604.06280v1 Announce Type: cross Abstract: Purpose: To develop and evaluate DosimeTron, an agentic AI system for automated patient-specific MC internal radiation dosimetry in PET/CT examination
arXiv:2601.05524v2 Announce Type: replace Abstract: Parallel Speculative Decoding (PSD) accelerates traditional Speculative Decoding (SD) by overlapping draft generation with verification. However, it
arXiv:2604.07986v1 Announce Type: new Abstract: Egocentric video is crucial for next-generation 4D scene reconstruction, with applications in AR/VR and embodied AI. However, reconstructing dynamic fir
arXiv:2604.05350v2 Announce Type: replace Abstract: Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user repo
arXiv:2509.01986v4 Announce Type: replace-cross Abstract: In recent years, integrating multimodal understanding and generation into a single unified model has emerged as a promising paradigm. While th
arXiv:2604.03540v2 Announce Type: replace Abstract: Although multi-step generative policies achieve strong performance in robotic manipulation by modeling multimodal action distributions, they require
arXiv:2604.06333v1 Announce Type: new Abstract: Drifting models generate high-quality samples in a single forward pass by transporting generated samples toward the data distribution using a vector val
arXiv:2410.17473v2 Announce Type: replace Abstract: In reinforcement learning (RL), temporal difference (TD) error is known to be related to the firing rate of dopamine neurons. It has been observed t
arXiv:2604.07965v1 Announce Type: new Abstract: Model editing aims to update knowledge to add new concepts and change relevant information without retraining. Lifelong editing is a challenging task, p
arXiv:2512.03745v2 Announce Type: replace Abstract: Two-stage learning pipeline has achieved promising results in unsupervised visible-infrared person re-identification (USL-VI-ReID). It first perform
arXiv:2604.08075v1 Announce Type: new Abstract: Production vLLM fleets typically provision each instance for the worst-case context length, leading to substantial KV-cache over-allocation and under-ut
arXiv:2601.07994v4 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts. While recent LLMs support extended context wi
arXiv:2604.07147v1 Announce Type: cross Abstract: Large language models produce repetitive output when prompted independently across many batches, a phenomenon we term cross-batch mode collapse: the p
arXiv:2604.06596v1 Announce Type: cross Abstract: Semi-supervised learning aims to infer class labels using only a small fraction of labeled data. In graph-based semi-supervised learning, this is typi
arXiv:2604.08543v1 Announce Type: new Abstract: Event cameras offer multiple advantages in monocular egocentric 3D human pose estimation from head-mounted devices, such as millisecond temporal resolut
arXiv:2510.14509v3 Announce Type: replace-cross Abstract: The rapid advancement in large language models (LLMs) has demonstrated significant potential in End-to-End Software Development (E2ESD). Howev
arXiv:2602.13669v4 Announce Type: replace Abstract: Recent multi-modal video generation models have achieved high visual quality, but their prohibitive latency and limited temporal stability hinder re
arXiv:2510.05261v2 Announce Type: replace Abstract: The Lipschitz constant is a key measure for certifying the robustness of neural networks to input perturbations. However, computing the exact consta
arXiv:2507.06949v3 Announce Type: replace Abstract: Ancient populations inhabited and transformed neotropical forests, yet the spatial extent of their ecological influence remains underexplored at hig
arXiv:2604.08213v1 Announce Type: new Abstract: High-quality training triplets (source-target image pairs with precise editing instructions) are a critical bottleneck for scaling instruction-guided im
arXiv:2604.08063v1 Announce Type: new Abstract: Reconstructing visual stimuli from non-invasive electroencephalography (EEG) remains challenging due to its low spatial resolution and high noise, parti
arXiv:2604.07659v1 Announce Type: new Abstract: Large language models (LLMs) hold significant promise for healthcare, yet their reliability in high-stakes clinical settings is often compromised by hal
arXiv:2604.07239v1 Announce Type: cross Abstract: While Learned Data Compression (LDC) has achieved superior compression ratios, balancing precise probability modeling with system efficiency remains c
arXiv:2505.15960v3 Announce Type: replace Abstract: Process Reward Models (PRMs) have emerged as a promising approach for improving LLM reasoning capabilities by providing process supervision over rea
arXiv:2604.08052v1 Announce Type: new Abstract: Linguistic steganography involves embedding secret messages within seemingly innocuous texts to enable covert communication. Provable security, which is
arXiv:2604.06515v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) allows scaling of language and vision models efficiently by activating only a small subset of experts per input. While
arXiv:2604.07607v1 Announce Type: cross Abstract: Robot learning increasingly depends on large and diverse data, yet robot data collection remains expensive and difficult to scale. Egocentric human da
arXiv:2604.06958v1 Announce Type: cross Abstract: Reliable radar pulse classification is essential in Electromagnetic Warfare for situational awareness and decision support. Deep Neural Networks have
arXiv:2604.08292v1 Announce Type: new Abstract: The autonomous operation of tracked mobile manipulators in rescue missions requires not only ensuring the reachability and safety of robot motion but al
arXiv:2604.07003v1 Announce Type: new Abstract: Large language models (LLMs) has been widely used for automated negotiation, but their high computational cost and privacy risks limit deployment in pri
arXiv:2604.07729v1 Announce Type: cross Abstract: Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore imp
arXiv:2604.07549v1 Announce Type: new Abstract: Conversational diagnosis prediction requires models to track evolving evidence in streaming clinical conversations and decide when to commit to a diagno
arXiv:2604.07490v1 Announce Type: new Abstract: Representation learning for geospatial and spatio-temporal data plays a critical role in enabling general-purpose geospatial intelligence. Recent geospa
arXiv:2604.07180v1 Announce Type: cross Abstract: We propose a geometric framework for longitudinal multi-parametric MRI analysis based on patient-specific energy modelling in sequence space. Rather t
arXiv:2604.06893v1 Announce Type: cross Abstract: Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy
arXiv:2604.07133v1 Announce Type: cross Abstract: This paper focuses on energy savings in downlink operation of cell-free massive MIMO (CF mMIMO) networks under dynamic traffic conditions. We propose
arXiv:2509.26522v3 Announce Type: replace Abstract: Reasoning LLMs show improved performance with longer chains of thought. However, recent work has highlighted their tendency to overthink, continuing