Knowledge catalogue
arXiv:2604.12911v1 Announce Type: cross Abstract: Multilingual benchmarks guide the development of frontier models. Yet multilingual evaluations reported by frontier models are structured similar to p
arXiv:2603.07436v2 Announce Type: replace Abstract: Training-free one-shot segmentation offers a scalable alternative to expert annotations where knowledge is often transferred from support images and
arXiv:2604.12634v1 Announce Type: new Abstract: Large language models (LLMs) face a fundamental trade-off between computational efficiency (e.g., number of parameters) and output quality, especially w
arXiv:2604.12319v1 Announce Type: new Abstract: Multimodal semantic segmentation has emerged as a powerful paradigm for enhancing scene understanding by leveraging complementary information from multi
arXiv:2601.07177v2 Announce Type: replace-cross Abstract: Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs). Most prior work focuses on imp
arXiv:2604.12667v1 Announce Type: new Abstract: Human-robot collaborative manufacturing, a core aspect of Industry 5.0, emphasizes ergonomics to enhance worker well-being. This paper addresses the dyn
arXiv:2509.18127v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations into monosemantic features. However, un
arXiv:2604.12500v1 Announce Type: new Abstract: Specification gaming under Reinforcement Learning (RL) is known to cause LLMs to develop sycophantic, manipulative, or deceptive behavior, yet the condi
arXiv:2512.04585v3 Announce Type: replace Abstract: Segment Anything Model 3 (SAM3) advances open-vocabulary segmentation through promptable concept segmentation, enabling users to segment all instanc
arXiv:2604.12013v1 Announce Type: new Abstract: Modern large language models generate text autoregressively, producing tokens one at a time. To study the learnability of such systems, Joshi et al. (CO
arXiv:2604.12350v1 Announce Type: cross Abstract: Molecular property optimization is central to drug discovery, yet many deep learning methods rely on black-box scoring and offer limited control over
arXiv:2602.05791v2 Announce Type: replace Abstract: Learning-based whole-body controllers have become a key driver for humanoid robots, yet most existing approaches require robot-specific training. In
arXiv:2604.12565v1 Announce Type: cross Abstract: Robots deployed in unstructured environments must coordinate whole-body motion -- simultaneously moving a mobile base and arm -- to interact with the
arXiv:2511.06341v2 Announce Type: replace Abstract: Control barrier functions (CBFs) are a popular tool for safety certification of nonlinear dynamical control systems. Recently, CBFs represented as n
arXiv:2411.19392v3 Announce Type: replace Abstract: Most Graph Neural Networks (GNNs) operate at the first-order scale, even though multi-scale representations are known to be crucial in domains such
arXiv:2604.12446v1 Announce Type: cross Abstract: Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems i
arXiv:2604.12752v1 Announce Type: new Abstract: In-context learning (ICL) enables medical image segmentation models to adapt to new anatomical structures from limited examples, reducing the clinical a
arXiv:2604.13035v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) increasingly generate indoor scenes through intermediate structures such as layouts and
arXiv:2604.11835v1 Announce Type: cross Abstract: Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of struc
arXiv:2604.12377v1 Announce Type: cross Abstract: Korean is a morphologically rich language with a featural writing system in which each character is systematically composed of subcharacter units know
arXiv:2602.08590v4 Announce Type: replace Abstract: Vision-language pretrained models offer strong transferable representations, yet adapting them in privacy-sensitive multi-party settings is challeng
arXiv:2604.12502v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) in multimodal tracking reveals a concerning trend where recent performance gains are often achieved at the cost
arXiv:2510.10073v2 Announce Type: replace-cross Abstract: Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed
arXiv:2604.12408v1 Announce Type: cross Abstract: Autonomous vehicles (AVs) promise efficient, clean and cost-effective transportation systems, but their reliance on sensors, wireless communications,
arXiv:2604.13019v1 Announce Type: new Abstract: Computer Use Agents (CUAs) fundamentally rely on graphical user interface (GUI) grounding to translate language instructions into executable screen acti
arXiv:2509.26404v2 Announce Type: replace-cross Abstract: Fingerprinting Large Language Models (LLMs)is essential for provenance verification and model attribution. Existing fingerprinting methods are
arXiv:2604.12322v1 Announce Type: new Abstract: The push for efficient text to image synthesis has moved the field toward one step sampling, yet existing methods still face a three way tradeoff among
arXiv:2604.12002v1 Announce Type: new Abstract: Current post-training methods in verifiable settings fall into two categories. Reinforcement learning (RLVR) relies on binary rewards, which are broadly
arXiv:2604.11914v1 Announce Type: new Abstract: Self-monitoring capabilities -- metacognition, self-prediction, and subjective duration -- are often proposed as useful additions to reinforcement learn
arXiv:2505.18646v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks. To enable LLMs to address more complex coding challenge
arXiv:2602.15876v1 Announce Type: cross Abstract: Adapting instruction to the fine-grained needs of individual students is a powerful application of recent advances in large language models. These gen
arXiv:2503.10471v2 Announce Type: replace-cross Abstract: Predicting crystal structures from chemical compositions is a fundamental challenge in materials discovery, complicated by complex 3D geometri
arXiv:2603.01045v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agen
arXiv:2507.08977v4 Announce Type: replace-cross Abstract: Scientific modeling faces a tradeoff between the interpretability of mechanistic theory and the predictive power of machine learning. While ex
arXiv:2410.01473v2 Announce Type: replace Abstract: Soil sinkholes significantly influence soil degradation, infrastructure vulnerability, and landscape evolution. However, their irregular shapes, com
arXiv:2604.12040v1 Announce Type: cross Abstract: We present SIR-Bench, a benchmark of 794 test cases for evaluating autonomous security incident response agents that distinguishes genuine forensic in
arXiv:2506.14512v4 Announce Type: replace Abstract: Large Language Models (LLMs) have undergone rapid progress, largely attributed to reinforcement learning on complex reasoning tasks. In contrast, wh
arXiv:2603.12583v2 Announce Type: replace Abstract: In this work, we propose a data-driven framework to design optimal haptic nudge feedback leveraging the learner's estimated skill to address the cha
arXiv:2506.00239v5 Announce Type: replace Abstract: The ability of AI to sense and identify various substances based on their smell alone can have profound impacts on allergen detection (e.g. smelling
arXiv:2604.12617v1 Announce Type: cross Abstract: The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL)
arXiv:2604.12482v1 Announce Type: cross Abstract: Optimizing the body and brain of a robot is a coupled challenge: the morphology determines what control strategies are effective, while the control pa
arXiv:2604.12245v1 Announce Type: cross Abstract: Deep neural networks, despite their high accuracy, often exhibit poor confidence calibration, limiting their reliability in high-stakes applications.
arXiv:2604.12110v1 Announce Type: new Abstract: Recent advances in recommendation scaling laws have led to foundation models of unprecedented complexity. While these models offer superior performance,
arXiv:2604.12254v1 Announce Type: cross Abstract: SpanKey is a lightweight way to gate inference without encrypting weights or chasing leaderboard accuracy on gated inference. The idea is to condition
arXiv:2603.23998v2 Announce Type: replace Abstract: Existing approaches to increasing the effective depth of Transformers predominantly rely on parameter reuse, extending computation through recursive
arXiv:2511.22039v3 Announce Type: replace Abstract: This paper introduces a novel architecture for trajectory-conditioned forecasting of future 3D scene occupancy. In contrast to methods that rely on
arXiv:2604.12102v1 Announce Type: new Abstract: We introduce compute-grounded reasoning (CGR), a design paradigm for spatial-aware research agents in which every answerable sub-problem is resolved by
arXiv:2604.12600v1 Announce Type: new Abstract: The core challenge of hyperspectral image denoising is striking the right balance between data fidelity and noise prior modeling. Most existing methods
arXiv:2412.07238v3 Announce Type: replace Abstract: The identity of a speaker influences language comprehension through modulating perception and expectation. This review explores speaker effects and
arXiv:2604.12247v1 Announce Type: cross Abstract: Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, w
arXiv:2506.01979v4 Announce Type: replace-cross Abstract: Recently, speculative decoding (SD) has emerged as a promising technique to accelerate LLM inference by employing a small draft model to propo
arXiv:2510.20093v2 Announce Type: replace-cross Abstract: Although recent advancements in diffusion models have significantly enriched the quality of generated images, challenges remain in synthesizin
arXiv:2604.03136v4 Announce Type: replace Abstract: As AI-generated fiction becomes increasingly prevalent, questions of authorship and originality are becoming central to how written work is evaluate
arXiv:2604.12746v1 Announce Type: new Abstract: Stress remains a significant social problem for individuals in modern societies. This paper presents a machine learning approach for the automatic detec
arXiv:2604.12575v1 Announce Type: new Abstract: This paper introduces StructDiff, a generative framework based on a single-scale diffusion model for single-image generation. Single-image generation ai
arXiv:2604.12257v1 Announce Type: new Abstract: Underwater Image Enhancement (UIE) is essential for robust visual perception in marine applications. However, existing methods predominantly rely on uni
arXiv:2604.11890v1 Announce Type: new Abstract: We study signal propagation at initialization in transformers through the averaged partial Jacobian norm (APJN), a measure of gradient amplification acr
arXiv:2604.12273v1 Announce Type: cross Abstract: Flow matching has emerged as a powerful generative framework, with recent few-step methods achieving remarkable inference acceleration. However, we id
arXiv:2309.13904v3 Announce Type: replace Abstract: Unsupervised anomaly localization aims to identify anomalous regions that deviate from normal sample patterns. Most recent methods perform feature m
arXiv:2502.06595v3 Announce Type: replace-cross Abstract: Diffusion kernels over graphs have been widely utilized as effective tools in various applications due to their ability to accurately model th