Knowledge catalogue
arXiv:2605.22420v1 Announce Type: new Abstract: Urban scene reconstruction from real-world observations has emerged as a powerful tool for self-driving development and testing. While current neural re
arXiv:1709.03806v2 Announce Type: replace Abstract: Modern vision models have achieved strong object-recognition performance, yet it remains unclear whether their representations encode object-level s
arXiv:2605.22138v1 Announce Type: cross Abstract: How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thou
arXiv:2605.22036v1 Announce Type: new Abstract: Despite significant progress in Vision-Language Navigation (VLN), existing approaches still rely on dense RGB videos that produce excessive patch tokens
arXiv:2510.00948v2 Announce Type: replace Abstract: Real-world videos often extend over thousands of frames. Existing generative video super-resolution (VSR) approaches, however, face two persistent c
arXiv:2605.22504v1 Announce Type: cross Abstract: Collaborative driving aims to improve safety and efficiency by enabling connected vehicles to coordinate under partial observability. Recent approache
arXiv:2605.22089v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving. However, existing VLAs typically rely on sp
arXiv:2605.22121v1 Announce Type: new Abstract: Magnetic resonance imaging (MRI) is highly susceptible to patient motion due to its relatively long acquisition times and the fact that data are acquire
arXiv:2605.22190v1 Announce Type: new Abstract: Recent feed-forward 3D gaussian splatting methods have made dramatic progress on individual aspects of 3D scene reconstruction, but no existing method j
arXiv:2605.22104v1 Announce Type: new Abstract: Real-world image restoration is challenging due to complex and interacting mixed degradations. Recent agent-based approaches address this problem by com
arXiv:2605.21981v1 Announce Type: new Abstract: Flow matching with x-prediction -- regressing the clean data point rather than the ambient velocity -- is known to exploit low-dimensional manifold stru
arXiv:2605.22538v1 Announce Type: new Abstract: Traditional visual object tracking (VOT) methods typically rely on task-specific supervised training, limiting their generalization to unseen objects an
arXiv:2512.10719v2 Announce Type: replace Abstract: End-to-end autonomous driving methods built on vision language models (VLMs) have undergone rapid development driven by their universal visual under
arXiv:2605.22217v1 Announce Type: cross Abstract: Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent s
arXiv:2605.21882v1 Announce Type: new Abstract: Vision-language models (VLMs) often fail under low illumination because their visual grounding is learned predominantly from RGB imagery, whereas therma
arXiv:2605.22403v1 Announce Type: new Abstract: Surface electromyography (sEMG) signal-based activity recognition has attracted increasing research attention in recent years. To develop accurate sEMG
arXiv:2605.22769v1 Announce Type: new Abstract: Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal groun
arXiv:2602.02112v2 Announce Type: replace-cross Abstract: Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality dep
arXiv:2605.20237v1 Announce Type: new Abstract: We present a lightweight appearance adapter for Stable Diffusion that enables controllable and consistent anime character generation under diverse editi
arXiv:2605.20915v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific training data from a model while preserving reliable behavior on the remaining data, making
arXiv:2605.20971v1 Announce Type: new Abstract: The growing sophistication of GAN-based image manipulation presents significant challenges for digital forensics. This study compares the performance of
arXiv:2605.20689v1 Announce Type: new Abstract: High-dimensional embeddings from large language models impose significant storage and computational costs on vector search systems. Recent embedding com
arXiv:2601.03019v4 Announce Type: replace-cross Abstract: DNA language models are increasingly used to represent genomic sequence, yet their effectiveness depends critically on how raw nucleotides are
arXiv:2605.20569v1 Announce Type: new Abstract: Hyperspectral imagery encodes rich material properties that can improve tracking robustness under appearance ambiguity, illumination change, and backgro
arXiv:2605.20536v1 Announce Type: new Abstract: Accurate classification of breast ultrasound images into benign, malignant, and normal categories is a critical clinical task complicated by speckle noi
arXiv:2605.20362v1 Announce Type: new Abstract: Virtual staining of histopathology images (e.g., H&E-IHC) is an emerging tool in digital pathology, enabling faster and cheaper workflows by synthesizin
arXiv:2603.22430v2 Announce Type: replace Abstract: Offline Reinforcement Learning (RL) learns optimal policies from fixed datasets, training a policy once and deploying it at inference time without f
arXiv:2605.20799v1 Announce Type: cross Abstract: We present Overall FLOP Utilization (OFU), a hardware-level, precision-agnostic GPU efficiency metric for AI workloads on HPC systems, derived from tw
arXiv:2605.20948v1 Announce Type: new Abstract: Scaling conditional memory offers a promising way to increase language-model capacity, but existing methods such as Engram learn large memory tables fro
arXiv:2605.20798v1 Announce Type: cross Abstract: Narang et al. (2021) evaluated 40+ Transformer modifications at T5-base scale and concluded that most did not transfer. Five years later, the typical
arXiv:2605.20302v1 Announce Type: cross Abstract: Supervised classification has a theoretical optimum, Neural Collapse (NC), yet neither of its two dominant paradigms reaches it in practice. Cross ent
arXiv:2605.20187v1 Announce Type: new Abstract: Understanding dependencies between variables is critical for interpretability and efficient generation in masked diffusion models (MDMs), yet these mode
arXiv:2605.20342v1 Announce Type: new Abstract: Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promisin
arXiv:2605.20708v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization,
arXiv:2605.21190v1 Announce Type: new Abstract: Despite the generative capabilities of diffusion and flow models, real-image editing remains constrained by a persistent trade-off between semantic edit
arXiv:2602.06358v2 Announce Type: replace Abstract: We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapte
arXiv:2605.21147v1 Announce Type: cross Abstract: As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large langua
arXiv:2605.20296v1 Announce Type: new Abstract: Fine-tuning a language model for a target task routinely degrades capabilities the training data never explicitly threatened. We study this phenomenon,
arXiv:2605.20929v1 Announce Type: new Abstract: We propose STEAM (Spatial, Temporal, and Emergent congestion Awareness for MAPF), a training-free test-time enhancement framework for learning-based dec
arXiv:2605.20356v1 Announce Type: new Abstract: Full-duplex spoken dialogue models (SDMs) can listen and speak simultaneously, enabling interaction dynamics closer to human conversation than turn-base
arXiv:2605.20581v1 Announce Type: new Abstract: Machine learning interatomic potentials (MLIPs) achieve excellent accuracy when trained on large Density Functional Theory (DFT) data. To be useful in p
arXiv:2605.20901v1 Announce Type: new Abstract: We propose VISTA, a V-JEPA Integrated StillFast Temporal Anticipator for the Ego4D Short-Term Object Interaction Anticipation (STA) Challenge at EgoVis
arXiv:2603.14392v2 Announce Type: replace Abstract: Trajectory world models play a crucial role in robotic dynamics learning, planning, and control. While recent works have explored trajectory world m
arXiv:2605.20306v1 Announce Type: new Abstract: We introduce WildRoadBench, a wild aerial road-damage grounding benchmark that couples direct visual grounding by vision-language models with autonomous
arXiv:2605.19698v1 Announce Type: cross Abstract: Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are
arXiv:2605.20127v1 Announce Type: cross Abstract: Artificial vision models are often evaluated against the human visual cortex by measuring how accurately their internal representations predict brain
arXiv:2505.16819v4 Announce Type: replace Abstract: Recent advances in scene-based video generation enable coherent visual narratives from structured prompts, yet a key aspect of storytelling -- chara
arXiv:2605.18916v1 Announce Type: cross Abstract: We investigate Counterfactual Video Foley Generation, which aims to adopt a sound-source identity that contradicts the visual evidence while remaining
arXiv:2605.20036v1 Announce Type: new Abstract: Ride-hailing platforms like DiDi Chuxing operate in highly dynamic environments where balancing driver supply and passenger demand is critical. Although
arXiv:2511.12158v3 Announce Type: replace Abstract: Research in bioacoustics, neuroscience, and linguistics often uses birdsong as a proxy to acquire knowledge across diverse areas. This requires audi
arXiv:2605.18855v1 Announce Type: cross Abstract: Attention Residuals replace standard additive residual connections with learned softmax attention over previous layer outputs, enabling selective cros
arXiv:2605.18871v1 Announce Type: cross Abstract: When Large Language Models produce structured outputs such as travel plans, code solutions, or multi-step proofs, individual reasoning steps may appea
arXiv:2510.12773v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) process every token through all layers of a transformer stack, causing wasted computation on simple queries and i
arXiv:2605.19527v1 Announce Type: new Abstract: Occluded person re-identification focuses on matching partially visible pedestrians across multiple camera views. However, occlusions disrupt body-regio
arXiv:2601.05391v2 Announce Type: replace Abstract: Accurate multistep forecasting of node-level attributes on dynamic graphs is critical for applications ranging from financial trust networks to biol
arXiv:2605.19842v1 Announce Type: new Abstract: We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation. Unlike conventional tensor decomp
arXiv:2605.20022v1 Announce Type: new Abstract: Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and
arXiv:2605.18795v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning of large language models, yet most variants target dense architectures. Mixture-o
arXiv:2605.19999v1 Announce Type: cross Abstract: Benchmark datasets are critical for reproducible, reliable, and discriminative evaluation of LLMs. However, recent studies reveal that many benchmark
arXiv:2605.19018v1 Announce Type: new Abstract: Fine-tuning adapts a pre-trained model to downstream tasks using a small amount of labeled data. Low-Rank Adaptation (LoRA) is an efficient fine-tuning