Self-Distilled RLVR
arXiv:2604.03128v2 Announce Type: replace Abstract: On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to pro
Knowledge catalogue
arXiv:2604.03128v2 Announce Type: replace Abstract: On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to pro
arXiv:2604.08532v1 Announce Type: new Abstract: Large-scale multi-view reconstruction models have made remarkable progress, but most existing approaches still rely on fully supervised training with gr
arXiv:2604.06996v1 Announce Type: cross Abstract: LLM-as-a-judge has become the de facto approach for evaluating LLM outputs. However, judges are known to exhibit self-preference bias (SPB): they tend
arXiv:2604.04958v2 Announce Type: replace-cross Abstract: Recent work suggests that large-scale, multi-animal modeling can significantly improve neural recording analysis. However, for functional calc
arXiv:2604.06389v1 Announce Type: new Abstract: Uncertainty estimation for reasoning language models remains difficult to deploy in practice: sampling-based methods are computationally expensive, whil
arXiv:2604.07054v2 Announce Type: replace Abstract: Sales dialogues require multi-turn, goal-directed persuasion under asymmetric incentives, which makes them a challenging setting for large language
arXiv:2604.08153v1 Announce Type: new Abstract: Unmanned Aerial Vehicles (UAVs) have emerged as a key enabler technology for data collection from Internet of Things (IoT) devices. However, effective d
arXiv:2604.08147v1 Announce Type: cross Abstract: Recent advances in audio-visual representation learning have shown the value of combining contrastive alignment with masked reconstruction. However, j
arXiv:2509.26036v3 Announce Type: replace Abstract: While Contrastive Language-Image Pretraining (CLIP) excels at zero-shot tasks by aligning image and text embeddings, its performance in few-shot cla
arXiv:2604.07766v1 Announce Type: new Abstract: We investigate a fundamental structural question in Grouped Query Attention (GQA) transformers: do the layers most sensitive to task correctness coincid
arXiv:2604.06204v1 Announce Type: cross Abstract: Personalization is essential for Large Language Model (LLM)-based agents to adapt to users' preferences and improve response quality and task performa
arXiv:2604.06900v1 Announce Type: cross Abstract: The field of cybersecurity is confronted with two interrelated challenges: a worldwide deficit of qualified practitioners and ongoing human-factor wea
arXiv:2604.07737v1 Announce Type: new Abstract: While transformer-based Large Language Models (LLMs) theoretically support massive context windows, they suffer from severe performance degradation when
arXiv:2604.06346v1 Announce Type: cross Abstract: Large language models have shown strong potential for Arabic medical text generation; however, traditional fine-tuning objectives treat all medical ca
arXiv:2508.16703v4 Announce Type: replace-cross Abstract: On-device running Large Language Models (LLMs) is nowadays a critical enabler towards preserving user privacy. We observe that the attention o
arXiv:2604.06636v1 Announce Type: cross Abstract: Process supervision has emerged as a promising approach for enhancing LLM reasoning, yet existing methods fail to distinguish meaningful progress from
arXiv:2603.13970v2 Announce Type: replace Abstract: In High Energy Physics, as in many other fields of science, the application of machine learning techniques has been crucial in advancing our underst
arXiv:2604.07936v1 Announce Type: new Abstract: Stain variability is a pervasive source of distribution shift and potential shortcut learning in renal pathology AI. We ask whether lupus nephritis glom
arXiv:2604.08544v1 Announce Type: cross Abstract: Robotic manipulation with deformable objects represents a data-intensive regime in embodied learning, where shape, contact, and topology co-evolve in
arXiv:2604.08377v1 Announce Type: cross Abstract: Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after depl
arXiv:2604.06550v1 Announce Type: cross Abstract: OpenClaw's ClawHub marketplace hosts over 13,000 community-contributed agent skills, and between 13% and 26% of them contain security vulnerabilities
arXiv:2604.06811v1 Announce Type: cross Abstract: Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamin
arXiv:2604.07316v1 Announce Type: new Abstract: The growing complexity of neural networks hinders the deployment of distributed machine learning on resource-constrained devices. Split learning (SL) of
arXiv:2409.01633v4 Announce Type: replace-cross Abstract: An effective integration of rich feature representations with robust classification mechanisms remains a key challenge in visual understanding
arXiv:2604.08120v1 Announce Type: cross Abstract: Adapting Multimodal Large Language Models (MLLMs) for hour-long videos is bottlenecked by context limits. Dense visual streams saturate token budgets
arXiv:2604.07171v1 Announce Type: new Abstract: Decision-making in military aviation Prognostics and Health Management (PHM) faces significant challenges due to the 'curse of dimensionality' in large-
arXiv:2604.07477v1 Announce Type: new Abstract: For applications including facial identification, forensic analysis, photographic improvement, and medical imaging diagnostics, facial image deblurring
arXiv:2307.03571v4 Announce Type: replace Abstract: We present a framework for smooth optimization of explicitly regularized objectives for (structured) sparsity. These non-smooth and possibly non-con
arXiv:2504.13378v2 Announce Type: replace-cross Abstract: Generating high-quality, photorealistic textures for 3D human avatars remains a fundamental yet challenging task in computer vision and multim
arXiv:2604.06265v1 Announce Type: new Abstract: Quantum-inspired tensor networks algorithms have shown to be effective and efficient models for machine learning tasks, including anomaly detection. Her
arXiv:2604.06523v1 Announce Type: cross Abstract: Quantum operations on pure states can be fully represented by unitary matrices. Variational quantum circuits, also known as quantum neural networks, e
arXiv:2604.08368v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, enable scalable adaptation of foundation models by injecting low-rank adapters. However,
arXiv:2604.05933v3 Announce Type: replace Abstract: Ultrasound perception typically requires multiple scan views through probe movement to reduce diagnostic ambiguity, mitigate acoustic occlusions, an
arXiv:2601.16294v2 Announce Type: replace-cross Abstract: General Matrix Multiplication (GEMM) is the cornerstone of HPC workloads and Deep Learning. State-of-the-art vendor libraries tune tensor layo
arXiv:2604.06774v1 Announce Type: cross Abstract: Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theori
arXiv:2512.23365v3 Announce Type: replace Abstract: The rapid progress of Multimodal Large Language Models (MLLMs) has unlocked the potential for enhanced 3D scene understanding and spatial reasoning.
arXiv:2604.07592v1 Announce Type: new Abstract: Embodied-AI agents must reason about how objects move and interact in 3-D space over time, yet existing smaller frontier Large Language Models (LLMs) st
arXiv:2604.06482v1 Announce Type: cross Abstract: Time-resolved volumetric MR imaging that reconstructs a 3D MRI within sub-seconds to resolve deformable motion is essential for motion-adaptive radiot
arXiv:2511.11663v2 Announce Type: replace-cross Abstract: The emergence of accurate open large language models (LLMs) has sparked a push for advanced quantization techniques to enable efficient deploy
arXiv:2604.06256v1 Announce Type: cross Abstract: Training dynamics during grokking concentrate along a small number of dominant update directions -- the spectral edge -- which reliably distinguishes
arXiv:2601.23155v2 Announce Type: replace-cross Abstract: Information-based data selection for instruction tuning is compelling: maximizing the log-determinant of the Fisher information yields a monot
arXiv:2503.02642v3 Announce Type: replace-cross Abstract: In both machine learning and in computational neuroscience, plasticity in functional neural networks is frequently expressed as gradient desce
arXiv:2604.07177v1 Announce Type: cross Abstract: We investigate the feasibility of real-time 3D Gaussian Splatting (3DGS) rasterisation on edge clients with varying Gaussian splat counts and GPU comp
arXiv:2504.04640v3 Announce Type: replace Abstract: Variation in language use, shaped by speakers' sociocultural background and specific context of use, offers a rich lens into cultural perspectives,
arXiv:2604.07725v1 Announce Type: cross Abstract: We show that verifier-free evolution is bottlenecked by both diversity and efficiency: without external correction, repeated evolution accelerates col
arXiv:2506.11786v2 Announce Type: replace Abstract: Accurate real-time estimation of human movement dynamics, including internal joint moments and muscle forces, is essential for applications in clini
arXiv:2604.03647v2 Announce Type: replace-cross Abstract: In the unsupervised self-evolution of Multimodal Large Language Models, the quality of feedback signals during post-training is pivotal for st
arXiv:2603.04759v2 Announce Type: replace Abstract: The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse do
arXiv:2604.08185v1 Announce Type: new Abstract: Tensegrity robots offer compliance and adaptability, but their nonlinear, and underconstrained dynamics make state estimation challenging. Reliable cont
arXiv:2502.19559v3 Announce Type: replace Abstract: Multi-agent debate - multiple instances of large language models discussing problems in turn-based interaction - has shown promise for solving knowl
arXiv:2604.06714v1 Announce Type: new Abstract: AI applications driven by multimodal large language models (MLLMs) are prone to hallucinations and pose considerable risks to human users. Crucially, su
arXiv:2604.07923v1 Announce Type: new Abstract: Dynamic urban environments are often captured by cameras placed at spatially separated locations with little or no view overlap. However, most existing
arXiv:2604.06525v1 Announce Type: cross Abstract: Achieving optimal rates for stochastic composite convex optimization without prior knowledge of problem parameters remains a central challenge. In the
arXiv:2604.06366v1 Announce Type: new Abstract: Deep linear networks (DLNs) are used as an analytically tractable model of the training dynamics of deep neural networks. While gradient descent in DLNs
arXiv:2603.11394v2 Announce Type: replace Abstract: Patients and clinicians are increasingly using chatbots powered by large language models (LLMs) for healthcare inquiries. While state-of-the-art LLM
arXiv:2604.06836v2 Announce Type: new Abstract: Quantization is an effective way to reduce the memory cost of large-scale model training. However, most existing methods adopt fixed-precision policies,
arXiv:2604.07028v1 Announce Type: cross Abstract: Strategic interaction in adversarial domains such as law, diplomacy, and negotiation is mediated by language, yet most game-theoretic models abstract
arXiv:2604.06990v1 Announce Type: cross Abstract: Psychological stress is clinically relevant in cardio-oncology, yet it is typically assessed only through patient-reported outcome measures (PROMs) an
arXiv:2604.07100v1 Announce Type: cross Abstract: Empathetic dialogue requires not only recognizing a user's emotional state but also making strategy-aware, context-sensitive decisions throughout resp
arXiv:2604.06631v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training while preserving data privacy, but its practical deployment is hampered by system and sta