Knowledge catalogue
arXiv:2606.01985v1 Announce Type: new Abstract: Recent breakthroughs in instruction-based image editing have captured significant attention, as models are now capable of handling real-world editing de
arXiv:2601.22900v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning across domains, but outcome-only scalar rewards are often
arXiv:2606.00717v1 Announce Type: cross Abstract: Uncertainty quantification is essential in high-stakes machine learning tasks. However, one of the principled solutions, conformal prediction, faces c
arXiv:2606.00146v1 Announce Type: cross Abstract: Motion artifacts in magnetic resonance imaging (MRI) degrade diagnostic reliability. Existing deep learning methods are typically contrast-specific an
arXiv:2606.00399v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific training samples while preserving the model's utility. Existing single-objective approaches,
arXiv:2606.02162v1 Announce Type: cross Abstract: Document type classification in visually rich documents remains challenging, as relevant information is distributed across textual, visual, and layout
arXiv:2606.00471v1 Announce Type: new Abstract: Accurate pedestrian trajectory prediction is essential for safe navigation in autonomous driving and intelligent transportation systems. Despite substan
arXiv:2606.01084v1 Announce Type: cross Abstract: Combinatorial routing problems such as the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP) are fundamental NP-hard
arXiv:2606.00174v1 Announce Type: cross Abstract: Electromyography (EMG) directly reflects muscle activation and is a key sensing modality for gesture recognition, prosthetic control, and wearable int
arXiv:2510.14025v2 Announce Type: replace Abstract: Adversarial purification has achieved great success in combating adversarial image perturbations, which are usually assumed to be additive. However,
arXiv:2606.00809v1 Announce Type: new Abstract: Many real-world conversational settings for knowledge discovery, including podcasts, hiring screens, and marketplaces, require a purpose-driven understa
arXiv:2606.02223v1 Announce Type: new Abstract: Estimating the generative mechanism of large-scale networks is a fundamental challenge in statistical machine learning. It requires the identification o
arXiv:2510.03745v2 Announce Type: replace Abstract: Low-discrepancy points are designed to efficiently fill the space in a uniform manner. This uniformity is highly advantageous in many problems in sc
arXiv:2511.05913v2 Announce Type: replace-cross Abstract: New intent discovery (NID) seeks to recognize both new and known intents from unlabeled user utterances, which finds prevalent use in practica
arXiv:2606.01078v1 Announce Type: new Abstract: Transport MCMC trains a normalizing flow to precondition Metropolis--Hastings proposals, achieving high empirical efficiency on challenging posteriors;
arXiv:2411.11793v2 Announce Type: replace Abstract: In federated learning (FL), a central server typically allocates training efforts to clients. However, from a market-oriented perspective, clients m
arXiv:2606.02042v1 Announce Type: new Abstract: Continual industrial anomaly detection with diffusion models suffers from historical normality prior drift and catastrophic forgetting. Existing continu
arXiv:2606.02430v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into high-performance computing (HPC) workflows, accelerating scientific discovery through di
arXiv:2606.00820v1 Announce Type: new Abstract: Multi-agent debate (MAD) is a promising strategy for improving LLM reasoning, but when agents converge on a shared answer, it is unclear whether that co
arXiv:2606.02493v1 Announce Type: new Abstract: Large language models (LLMs) are being increasingly used to answer subjective, information-seeking questions, where users are sensitive to how responses
arXiv:2405.01930v2 Announce Type: replace Abstract: This paper introduces OARelatedWork: a dataset for related work generation from open-access sources. It is the first large-scale multi-document summ
arXiv:2606.01803v1 Announce Type: new Abstract: The explosive growth of Text-to-Image (T2I) models, from large-scale versions to lightweight, real-time ones, now faces diminishing marginal returns fro
arXiv:2606.02433v1 Announce Type: cross Abstract: The rapid development of LLMs has significantly advanced tabular question answering, but most systems cannot perform future-oriented numerical predict
arXiv:2606.01682v1 Announce Type: cross Abstract: Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small mo
arXiv:2606.01476v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitig
arXiv:2512.10339v2 Announce Type: replace Abstract: Inference-time steering adapts pretrained diffusion and flow models to new tasks without retraining, often utilizing ratio-of-densities construction
arXiv:2606.01075v1 Announce Type: new Abstract: Recent work suggests that large language models (LLMs) can improve through self-evolution (SE), using supervision signals generated by the model itself.
arXiv:2510.17532v2 Announce Type: replace Abstract: Predicting cancer treatment outcomes requires models that are both accurate and interpretable, particularly in the presence of heterogeneous clinica
arXiv:2606.01039v1 Announce Type: cross Abstract: On-policy distillation (OPD) is a widely used technique to transfer capabilities from capable teacher language models to the base student models, and
arXiv:2603.27645v2 Announce Type: replace Abstract: Open-vocabulary change detection (OVCD) seeks to recognize arbitrary changes of interest by enabling generalization beyond a fixed set of predefined
arXiv:2511.05650v2 Announce Type: replace-cross Abstract: Alignment has greatly improved large language models (LLMs)' output quality at the cost of diversity, yielding highly similar outputs across g
arXiv:2606.00499v1 Announce Type: new Abstract: Video generation models are becoming a scalable form of world models, but they mainly generate plausible motion rather than proactively control or optim
arXiv:2606.02178v1 Announce Type: cross Abstract: Recent advancements in generative AI have led to image editing models capable of producing realistic forgeries that evade traditional image forgery lo
arXiv:2606.00990v1 Announce Type: new Abstract: A mobile robot following a graph of known routes can make costly navigation errors when a temporary obstacle blocks a critical edge: waiting too long be
arXiv:2606.00515v1 Announce Type: cross Abstract: Contact-rich manipulation demands both high-level semantic reasoning and the safe regulation of high-frequency contact dynamics. While Vision-Language
arXiv:2606.01537v1 Announce Type: new Abstract: Clinical diagnosis often requires combining imaging with physiological measurements, yet deployed models typically operate on unimodal data. We present
arXiv:2606.01265v1 Announce Type: cross Abstract: This paper demonstrates the effectiveness of machine learning-driven optimization for designing application-specific GaN tri-gate FinFETs in vertical
arXiv:2603.22999v3 Announce Type: replace Abstract: Recent advances in visual language models have enabled autonomous agents for complex reasoning, tool use, and document understanding. However, exist
arXiv:2603.16142v2 Announce Type: replace Abstract: Large language models (LLMs) have recently been adopted as synthetic agents for public opinion simulation, offering a promising alternative to costl
arXiv:2606.01543v1 Announce Type: new Abstract: Data scarcity in multimodal pathology motivates unified generative models that synthesize modality-specific appearance while preserving anatomically coh
arXiv:2602.12080v2 Announce Type: replace Abstract: Despite recent advances in AI, event data collection in soccer still relies heavily on labor-intensive manual annotation. Although prior work has ex
arXiv:2604.05634v2 Announce Type: replace Abstract: Machine unlearning (MU) has become a critical technique for GenAI models' safe and compliant operation. While existing MU methods are effective, mos
arXiv:2404.01356v3 Announce Type: replace-cross Abstract: Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness
arXiv:2507.18863v2 Announce Type: replace-cross Abstract: Visual Automatic Speech Recognition (V-ASR) is a challenging task that involves interpreting spoken language solely from visual information, s
arXiv:2606.01649v1 Announce Type: new Abstract: Generating physically consistent 3D tabletop scenes is a fundamental yet underexplored problem for interactive and generalist robotic learning. The chal
arXiv:2606.01894v1 Announce Type: new Abstract: Accurate Remaining Useful Life prediction is critical for industrial predictive maintenance. However, real-world deployment is challenging due to the ir
arXiv:2606.01834v1 Announce Type: cross Abstract: Human Action Recognition (HAR) using WiFi Channel State Information (CSI) has gained increasing attention due to its non-contact, low-cost, and privac
arXiv:2606.01572v1 Announce Type: cross Abstract: Predicting patient-specific facial soft-tissue deformation is critical for iterative orthognathic surgery planning. However, current computational met
PixelDiT is a 1.3B parameter diffusion transformer model that generates images directly in pixel space without requiring a VAE (Variational Autoencoder), representing an alternative approach to tradit
arXiv:2505.17659v4 Announce Type: replace-cross Abstract: Safe and feasible trajectory planning is critical for real-world autonomous driving systems. However, existing learning-based planners rely he
arXiv:2602.01662v4 Announce Type: replace Abstract: Recent advances in vision-language models (VLMs) have enabled increasing progress in real-world robot manipulation. However, long-horizon manipulati
arXiv:2606.02073v1 Announce Type: new Abstract: Generating objects with specific symmetries is essential in various real-world scenarios. However, adapting existing 2D continuous representations to en
arXiv:2606.01788v1 Announce Type: new Abstract: Embodied visual navigation, where an agent perceives a complex environment and acts to reach a goal from raw sensory input, underpins a wide range of ap
arXiv:2606.01858v1 Announce Type: new Abstract: Users increasingly expect image generation models to quickly adapt to highly diverse and personalized requirements, such as producing images with distin
arXiv:2602.00415v2 Announce Type: replace Abstract: Memory is not merely a storage mechanism for intelligent systems, but a structure for organizing evidence and constraining belief. This is especiall
arXiv:2606.02388v1 Announce Type: cross Abstract: Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little superv
arXiv:2606.00491v1 Announce Type: cross Abstract: Deep learning-based CT segmentation systems often achieve high accuracy on clean benchmark images, but their performance may degrade under heterogeneo
arXiv:2602.08585v2 Announce Type: replace-cross Abstract: Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference. Current KV cache eviction methods typic
arXiv:2506.09035v2 Announce Type: replace Abstract: We introduce Princeton365, a large-scale diverse dataset of 365 videos with accurate camera pose. Our dataset bridges the gap between accuracy and d
arXiv:2602.06448v2 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based scientific agents have accelerated scientific discovery, yet they often suffer from significant inefficiencie