Knowledge catalogue
arXiv:2605.16937v1 Announce Type: new Abstract: Trajectory-controlled video generation has become essential for controllable video generation. While current methods perform well under small-view camer
arXiv:2505.07813v2 Announce Type: replace-cross Abstract: Large-scale, diverse robot datasets have emerged as a promising path toward enabling dexterous manipulation policies to generalize to novel en
arXiv:2605.16742v1 Announce Type: new Abstract: Cortical surface registration is often driven by local geometric descriptors (e.g., sulcal depth and curvature). While this approach achieves geometric
arXiv:2605.16327v1 Announce Type: cross Abstract: Risk-aware navigation in unknown environments is a fundamental challenge for autonomous vehicles operating in complex urban systems. To address this i
arXiv:2605.16444v1 Announce Type: cross Abstract: Accurate intraoperative and postoperative diagnosis of spread through air spaces (STAS) is essential for guiding surgical decisions and postoperative
arXiv:2603.04870v2 Announce Type: replace Abstract: Denoising in the sRGB image space is challenging due to large noise variability. Although end-to-end methods perform well, their effectiveness in re
arXiv:2605.16732v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) achieve state-of-the-art image generation quality but incur substantial memory and computational costs at inference. While
arXiv:2601.13839v2 Announce Type: replace Abstract: Social media imagery provides a low-latency source of situational information during natural and human-induced disasters, enabling rapid damage asse
arXiv:2603.12676v2 Announce Type: replace Abstract: Generalizing neural surrogate models across different PDE parameters remains difficult because changes in PDE coefficients often make learning harde
arXiv:2602.12015v2 Announce Type: replace Abstract: Deploying large language models for clinical Text-to-SQL requires distinguishing two qualitatively different causes of output diversity: (i) input a
arXiv:2510.11391v3 Announce Type: replace-cross Abstract: Recent agentic workflows automate professional document generation but focus narrowly on textual quality, overlooking structural and stylistic
arXiv:2605.16622v1 Announce Type: new Abstract: In modern deep learning, weight decay is often credited with 'stabilizing' training dynamics, diverging from its classical role as a static regularizati
arXiv:2601.11956v2 Announce Type: replace-cross Abstract: Reliable reasoning in Large Language Models (LLMs) is challenged by their propensity for hallucination. While augmenting LLMs with Knowledge G
arXiv:2605.17432v1 Announce Type: new Abstract: Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information tha
arXiv:2505.16278v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving (E2E-AD) demands effective processing of multi-view sensory data and robust handling of diverse and complex driv
arXiv:2605.16737v1 Announce Type: cross Abstract: End-to-End (E2E) autonomous driving models have shown growing capability in recent years, with performance improving on increasingly challenging bench
arXiv:2605.18023v1 Announce Type: new Abstract: Open-Vocabulary Object Detection (OVD) models break the limitations of closed-set detection, enabling the iden- tification of unseen categories through
arXiv:2604.07393v2 Announce Type: replace-cross Abstract: Accurate forecasting of industrial time series requires balancing predictive accuracy with physical plausibility under non-stationary operatin
arXiv:2605.17486v1 Announce Type: cross Abstract: Recent progress in Reinforcement Learning (RL) provides a principled approach to optimizing Vision-Language-Action (VLA) models, facilitating a shift
arXiv:2605.18316v1 Announce Type: new Abstract: Inferring time-varying graph structures from high-dimensional nodal observations is a fundamental problem arising in neuroscience, finance, climatology,
arXiv:2605.16882v1 Announce Type: new Abstract: Low-resource deployment constraints have made model quantization essential for deploying neural networks while preserving performance. Meanwhile, model
arXiv:2605.18512v1 Announce Type: new Abstract: In-context learning (ICL) is highly sensitive to which demonstrations appear in the prompt, but selecting them is expensive because the space of possibl
arXiv:2605.17580v1 Announce Type: new Abstract: Electrocardiogram (ECG)-based models have achieved strong performance in diagnostic tasks, yet they remain limited in modeling how cardiac dynamics evol
arXiv:2605.17470v1 Announce Type: new Abstract: Image super-resolution (SR) aims to reconstruct high-quality, high-resolution (HR) images from low-resolution (LR) inputs and plays a critical role in v
arXiv:2605.17327v1 Announce Type: cross Abstract: Fast and reliable initialization is critical for monocular visual-inertial navigation systems (VINS), as it establishes the starting conditions for su
arXiv:2512.04556v2 Announce Type: replace-cross Abstract: Image convolution with complex kernels is a fundamental operation in photography, scientific imaging, and animation effects, yet direct dense
arXiv:2605.18214v1 Announce Type: new Abstract: Collecting large-scale egocentric video datasets with dense spatial and temporal annotations is costly, slow, and often constrained by environmental bia
arXiv:2605.17489v1 Announce Type: new Abstract: Face Image Quality Assessment (FIQA) is a crucial control step in biometric pipelines. It ensures only reliable samples are processed to maintain system
arXiv:2511.07288v2 Announce Type: replace-cross Abstract: Learning complex policies with Reinforcement Learning (RL) is often hindered by instability and slow convergence, a problem exacerbated by the
arXiv:2603.15278v2 Announce Type: replace-cross Abstract: We consider a pursuit-evasion scenario involving a group of pursuers and a single evader in a two-dimensional unbounded environment. The pursu
arXiv:2508.07292v3 Announce Type: replace Abstract: Endoscopic diagnosis is an iterative process in which clinicians progressively acquire, compare, and verify local visual evidence before reaching a
arXiv:2508.02127v2 Announce Type: replace Abstract: Object detection in autonomous driving is frequently compromised by complex illumination. While event cameras offer a robust solution, they are susc
arXiv:2601.22530v2 Announce Type: replace Abstract: Large Language Models (LLMs) struggle with multi-step reasoning over structured tables. The primary reason is the lack of explicit supervision for i
arXiv:2605.17958v1 Announce Type: new Abstract: Code reasoning refers to the task of predicting the output of a program given its source code and specific inputs. It can measure the reasoning capabili
arXiv:2605.18233v1 Announce Type: new Abstract: Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce long
arXiv:2605.18703v1 Announce Type: new Abstract: Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robus
arXiv:2605.16745v1 Announce Type: new Abstract: This paper addresses the challenge of integrating 3D meshes as a native modality within Multimodal Large Language Models (MLLMs). Diffusion-based large
arXiv:2511.20857v2 Announce Type: replace-cross Abstract: Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critica
Excited to share our new paper: RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably LLMs often fail on inputs well within their advertised context lengths. We show that these fa
arXiv:2605.17721v1 Announce Type: new Abstract: Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions,
arXiv:2605.16975v1 Announce Type: cross Abstract: Electrocardiogram (ECG) foundation models pretrained on typical diagnostic 10-second ECG segments, have demonstrated strong transferability across a r
arXiv:2605.17531v1 Announce Type: new Abstract: Referring segmentation aims to segment the target objects in images or videos based on the textual query. Despite remarkable progress over the past year
arXiv:2605.17361v1 Announce Type: cross Abstract: Multi-agent systems (MAS) powered by large language models (LLMs) have emerged as a powerful paradigm for complex problem solving, where performance c
arXiv:2406.15797v2 Announce Type: replace-cross Abstract: Employing graph neural networks (GNNs) for graph clustering has shown promising results in deep graph clustering. However, existing methods di
arXiv:2605.17115v1 Announce Type: new Abstract: Biased manipulation of facts across regional and national media outlets complicates misinformation detection in diverse landscapes like India. This pape
arXiv:2605.16696v1 Announce Type: new Abstract: Face inpainting techniques recover missing or occluded facial regions in a visually realistic manner, but preserving the identity in the final output re
arXiv:2601.21350v2 Announce Type: replace Abstract: A reliable reward model is essential for aligning large language models with human preferences through reinforcement learning from human feedback. H
arXiv:2503.16492v3 Announce Type: replace-cross Abstract: ffective Human-Robot Interaction (HRI) is crucial for enhancing accessibility and usability in real-world robotics applications. However, exis
arXiv:2505.18991v3 Announce Type: replace Abstract: Pansharpening seeks to fuse high-resolution panchromatic (PAN) and low-resolution multispectral (LRMS) images into a single image with both fine spa
arXiv:2605.17447v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have shown strong promise on Optical Character Recognition (OCR), yet the sheer number of visual tokens required to enco
arXiv:2605.17767v1 Announce Type: cross Abstract: We study feature learning in two-layer neural networks within the linear-width regime, where the number of hidden neurons, sample size, and input dime
arXiv:2605.16350v1 Announce Type: cross Abstract: We rethink Federated Learning (FL) from a nested learning perspective, framing the core challenge as how to collaboratively learn optimization rules,
arXiv:2509.06984v3 Announce Type: replace-cross Abstract: Federated Learning with LoRA fine-tuning offers an efficient and privacy-aware solution for institutions to collaboratively leverage their lar
arXiv:2605.18028v1 Announce Type: cross Abstract: Federated fine-tuning of Large Language Models faces severe statistical heterogeneity. However, existing model-level defenses often overlook the root
arXiv:2505.20218v2 Announce Type: replace Abstract: Accurate and safe medication recommendations are critical for effective clinical decision-making, especially in multimorbidity cases. However, exist
arXiv:2605.17231v1 Announce Type: cross Abstract: Activation steering methods modify intermediate representations of language models to control output behavior, but universally assume the activation s
arXiv:2602.03784v2 Announce Type: replace Abstract: Long-context LLM agents often struggle with growing token, memory, and latency costs, making efficient context compression essential for practical d
arXiv:2605.18055v1 Announce Type: cross Abstract: Predicting spatial gene expression from routine H&E enables large-scale molecular profiling, yet current models treat this as isolated pointwise tasks
arXiv:2512.23070v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models enable scalable neural networks through conditional computation, offering enhanced effectiveness and efficiency for
arXiv:2601.06163v2 Announce Type: replace Abstract: The widespread adoption of text-to-image (T2I) diffusion models has raised concerns about their potential to generate copyrighted, inappropriate, or