Knowledge catalogue
arXiv:2605.00836v1 Announce Type: new Abstract: Sampling from Flow Matching generative models requires solving an ordinary differential equation (ODE) whose computational cost is dominated by neural n
arXiv:2605.01495v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding responses in external knowledge during inference. However, conve
arXiv:2509.24276v4 Announce Type: replace Abstract: Large language models (LLMs) excel at complex reasoning but remain limited by static and incomplete parametric knowledge. Retrieval-augmented genera
arXiv:2605.00371v1 Announce Type: cross Abstract: In this paper, we propose GaMMA, a state-of-the-art (SoTA) large multimodal model (LMM) designed to achieve comprehensive musical content understandin
arXiv:2601.22709v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significan
arXiv:2605.00876v1 Announce Type: cross Abstract: Vision-language models (VLMs) read an image and produce text in a single forward pass, whereas radiologists typically inspect an image several times a
arXiv:2603.28767v2 Announce Type: replace Abstract: Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally
arXiv:2605.02222v1 Announce Type: cross Abstract: We present Orbit-Space Geometric Probability Paths (OGPP), a particle-native flow-matching framework for generative modeling of particle systems. OGPP
arXiv:2605.01650v1 Announce Type: new Abstract: Reliable subnational population estimates are essential for applications, yet remain difficult where censuses are sparse, outdated or spatially coarse.
arXiv:2605.01256v1 Announce Type: new Abstract: A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge
arXiv:2605.02616v1 Announce Type: new Abstract: Salient Object Detection (SOD) remains an essential yet underexplored task in the era of large-scale vision models. Although foundation models like SAM
arXiv:2604.03190v2 Announce Type: replace Abstract: Transformer attention computes a single softmax-weighted average over values -- a one-pass estimate that cannot correct its own errors. We introduce
arXiv:2605.00845v1 Announce Type: cross Abstract: Knowledge Graph Question Answering (KGQA) has advanced through structured query generation, yet most efforts target RDF/SPARQL, leaving Cypher and pro
arXiv:2605.01688v1 Announce Type: new Abstract: Long-horizon conversational agents rely on memory systems with increasingly sophisticated retrieval mechanisms. However, retrieved fragments are typical
arXiv:2603.09625v2 Announce Type: replace Abstract: Deep learning models benefit from increasing data diversity and volume, motivating synthetic data augmentation to improve existing datasets. However
arXiv:2504.10063v4 Announce Type: replace Abstract: Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models (LLMs). We introduce TOHA, a TOp
arXiv:2605.02596v1 Announce Type: new Abstract: With each sensing modality exhibiting inherent strengths and limitations, multi-modal approaches for wearable Human Activity Recognition (HAR) are becom
arXiv:2605.02169v1 Announce Type: new Abstract: We propose HeroCrystal, a novel privacy-preserving framework for multi-camera domain-adaptive object detection, addressing challenges such as data priva
arXiv:2508.12778v2 Announce Type: replace Abstract: Medical large vision-language Models (Med-LVLMs) have shown promise in clinical applications but suffer from factual inaccuracies and unreliable out
arXiv:2508.09179v3 Announce Type: replace-cross Abstract: Reconstructing high-fidelity MR images from undersampled k-space data remains a challenging problem in MRI. While Mamba variants for vision ta
arXiv:2602.13933v2 Announce Type: replace Abstract: Large language model (LLM) agents demonstrate strong performance in short-text contexts but often underperform in extended dialogues due to ineffici
arXiv:2605.01627v1 Announce Type: new Abstract: Low-rank decomposition is a compelling approach for compressing large language models, but its effectiveness hinges on selecting which singular-vector b
arXiv:2509.03540v3 Announce Type: replace Abstract: Large Language Models (LLMs) often struggle with producing factually consistent answers due to limitations in their parametric memory. Retrieval-Aug
arXiv:2605.00433v1 Announce Type: cross Abstract: Code generation, which aims to automatically generate source code from given programming requirements, has the potential to substantially improve soft
arXiv:2605.02409v1 Announce Type: new Abstract: Bayesian Optimization is an iterative method, tailored to optimizing expensive black box objective functions. Surrogate models like Gaussian Processes,
arXiv:2605.01402v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (
arXiv:2605.00572v1 Announce Type: new Abstract: Algorithm performance in combinatorial optimization is highly sensitive to parameter settings, while a single globally tuned configuration often fails t
arXiv:2512.21788v3 Announce Type: replace Abstract: Parameter-Efficient Fine-Tuning of Diffusion Transformers (DiTs) for diverse, multi-conditional tasks often suffers from task interference when usin
arXiv:2605.01409v1 Announce Type: cross Abstract: The growing availability of health-related instructional videos creates new opportunities for clinical training, patient rehabilitation, and health ed
arXiv:2503.09559v3 Announce Type: replace-cross Abstract: We introduce interlaced R2D2 (iR2D2), a DNN series paradigm for scalable image reconstruction from accelerated non-Cartesian k-space acquisiti
arXiv:2605.01036v1 Announce Type: new Abstract: This paper tackles the problem of physics-aware human motion synthesis in a dynamic scene. Unlike existing works which mainly tend to generate physicall
arXiv:2605.00940v1 Announce Type: new Abstract: A new interpretable experiential learning model based on state history and global feedback is presented. It is capable of learning a behavioral model re
arXiv:2412.15251v3 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are effective at capturing the semantics of short video content; however, they often fail to attend to the
arXiv:2602.07238v2 Announce Type: replace-cross Abstract: Do leading LLM developers possess a proprietary ``secret sauce'', or is LLM performance driven by scaling up compute? Using training and bench
arXiv:2605.02288v1 Announce Type: new Abstract: Automated laboratories hold the promise of accelerating scientific discovery, yet their deployment is bottlenecked by the difficulty of designing safe a
arXiv:2502.03814v5 Announce Type: replace Abstract: The rapid advancement of Large Language Models (LLMs) has opened new possibilities in Multi-Robot Systems (MRS), enabling enhanced communication, ta
arXiv:2605.02739v1 Announce Type: new Abstract: Dual-system Vision-Language-Action (VLA) models achieve state-of-the-art robotic manipulation but are bottlenecked by the VLM backbone, which must execu
arXiv:2605.00899v1 Announce Type: new Abstract: We present LatentDiff, a scalable framework for semantic dataset comparison that operates directly in the latent space of pretrained vision encoders. By
arXiv:2605.01058v1 Announce Type: cross Abstract: Layer-aligned distillation and convergence-based early exit represent two predominant computational efficiency paradigms for transformer inference; ye
arXiv:2605.01591v1 Announce Type: cross Abstract: Neural Ranking Models (NRMs) are central to modern information retrieval but remain highly vulnerable to adversarial manipulation. Existing attacks of
arXiv:2605.01735v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed in real-world systems, they must support post-hoc removal of specific content to meet privacy
arXiv:2605.00913v1 Announce Type: new Abstract: Sensor-based Human Activity Recognition (HAR) has attracted increasing attention in medical and healthcare monitoring, particularly with the growth of I
arXiv:2601.01322v2 Announce Type: replace Abstract: Modern Vision-Language Models (VLMs) achieve impressive performance but are limited by the quadratic complexity of self-attention, which prevents th
arXiv:2605.01047v1 Announce Type: cross Abstract: Hallucinations, outputs that sound plausible but are factually incorrect, remain an open challenge for deployed LLMs. In code generation, models frequ
arXiv:2605.01306v1 Announce Type: cross Abstract: Laser absorption spectroscopy (LAS) is a well-established technique for non-intrusive measurement of gas species in combustion and atmospheric environ
arXiv:2605.01347v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own trajectories under token-level teacher supervision, but existing methods are capped by a single
arXiv:2605.01805v1 Announce Type: cross Abstract: A key challenge in multi-agent reinforcement learning (MARL) lies in designing learning signals that effectively promote coordination among agents. De
arXiv:2605.02183v1 Announce Type: new Abstract: Adversarial training is effective on balanced datasets, but its robustness degrades under longtailed class distributions, where tail classes suffer high
arXiv:2605.00007v1 Announce Type: cross Abstract: Independent sample generation is the prevailing paradigm in modern diffusion-based generative models of AI. We ask a different question: can samples c
arXiv:2605.01386v1 Announce Type: new Abstract: Large Language Models (LLMs) lack persistent memory for long-term personalized conversations. Existing graph-based memory systems suffer from informatio
arXiv:2605.01967v1 Announce Type: cross Abstract: Deploying multimodal models in real-world scenarios requires generalization to new environments where recording conditions differ from training, a cha
arXiv:2508.11205v2 Announce Type: replace Abstract: Structure-preserving approaches to dynamics discovery have demonstrated great potential for modeling physical systems due to their use of strong ind
arXiv:2605.02444v1 Announce Type: new Abstract: Encoder-decoder imbalance and the reliance on large input volumes make many 3D brain tumor segmentation models both compute-heavy and brittle. We presen
arXiv:2605.00123v1 Announce Type: new Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts. Because we lack a robust understa
arXiv:2605.01579v1 Announce Type: cross Abstract: Empirical causal claims depend on many analyst decisions, from selecting covariates to choosing estimators. Existing robustness tools summarize how re
arXiv:2605.01520v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning
arXiv:2605.01766v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have revolutionized the landscape of AI, demonstrating impressive capabilities in tackling complex vision and
arXiv:2605.02438v1 Announce Type: new Abstract: Open-set supervised anomaly detection (OSAD) aims to identify unseen anomalies using limited anomalous supervision. However, existing prototype-based me
arXiv:2506.05952v4 Announce Type: replace Abstract: Recent advances in transformer-based text-to-motion generation have led to impressive progress in synthesizing high-quality human motion. Neverthele
arXiv:2510.08804v3 Announce Type: replace Abstract: We present MOSAIC, a multi-agent Large Language Model (LLM) framework for solving challenging scientific coding tasks. Unlike general-purpose coding