Positive-Only Drifting Policy Optimization
arXiv:2604.16519v1 Announce Type: new Abstract: In the field of online reinforcement learning (RL), traditional Gaussian policies and flow-based methods are often constrained by their unimodal express
Knowledge catalogue
arXiv:2604.16519v1 Announce Type: new Abstract: In the field of online reinforcement learning (RL), traditional Gaussian policies and flow-based methods are often constrained by their unimodal express
arXiv:2511.23170v5 Announce Type: replace Abstract: Contrastive vision-language pre-training frameworks such as CLIP have demonstrated impressive zero-shot performance across a range of vision-languag
arXiv:2604.17163v1 Announce Type: new Abstract: We propose PPEDCRF, a calibrated selective perturbation framework that protects background-based location privacy in released video frames against galle
arXiv:2604.17338v1 Announce Type: cross Abstract: Unlike code completion, debugging requires localizing faults and applying targeted edits. We observe that frontier LLMs often regenerate correct but o
arXiv:2604.16505v1 Announce Type: new Abstract: The selection of the optimal embryo for transfer is a critical yet challenging step in in vitro fertilization (IVF), primarily due to its reliance on th
arXiv:2604.18085v1 Announce Type: new Abstract: Matrix-level low-rank compression is a promising way to reduce the cost of large language models, but running compression and evaluating the resulting m
arXiv:2604.18316v1 Announce Type: cross Abstract: The most common cause of dementia is Alzheimer disease, a progressive neurodegenerative disorder affecting older adults that gradually impairs memory,
arXiv:2508.20751v2 Announce Type: replace Abstract: Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generati
arXiv:2506.13674v3 Announce Type: replace Abstract: Parameter-Efficient Fine-Tuning (PEFT) methods have become crucial for rapidly adapting large language models (LLMs) to downstream tasks. Prefix-Tun
arXiv:2511.07329v3 Announce Type: replace-cross Abstract: It introduces FractalNet, a fractal-inspired computational architectures for advanced large language model analysis that mainly challenges mod
arXiv:2604.16334v1 Announce Type: new Abstract: The use of Deep Neural Network based systems in the real world is growing. They have achieved state-of-the-art performance on many image, speech and tex
arXiv:2508.05132v2 Announce Type: replace Abstract: As medical LLMs transition to clinical deployment, assessing their ethical reasoning capability becomes critical. While achieving high accuracy on k
arXiv:2604.17670v1 Announce Type: new Abstract: We introduce Prior-Fitted Functional Flows, a generative foundation model for pharmacokinetics that enables zero-shot population synthesis and individua
arXiv:2604.16909v1 Announce Type: new Abstract: As large language models (LLMs) evolve from conversational assistants into agents capable of handling complex tasks, they are increasingly deployed in h
arXiv:2604.18354v1 Announce Type: new Abstract: Emotion plays a pivotal role in shaping negotiation outcomes, influencing trust, cooperation, and long-term relationships. Developing negotiation dialog
arXiv:2601.15220v2 Announce Type: replace Abstract: We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle
arXiv:2604.16523v1 Announce Type: new Abstract: This paper proposes a novel privacy-preserving semantic segmentation method that can use independent keys for each client and image. In the proposed met
arXiv:2510.16054v2 Announce Type: replace-cross Abstract: When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send th
arXiv:2510.18109v4 Announce Type: replace-cross Abstract: Evaluating the usefulness of data before purchase is essential when obtaining data for high-quality machine learning models, yet both model bu
arXiv:2604.17476v1 Announce Type: cross Abstract: Multi-user virtual reality enables immersive interaction. However, rendering avatars for numerous participants on each headset incurs prohibitive comp
arXiv:2505.14412v2 Announce Type: replace-cross Abstract: Effective prompt engineering remains a central challenge in fully harnessing the capabilities of LLMs. While well-designed prompts can dramati
arXiv:2604.17290v1 Announce Type: new Abstract: LLMs are widely used for code generation and mathematical reasoning tasks where they are required to generate structured output. They either need to rea
This post by Harrison Chase (creator of LangChain) likely discusses the concept of statements or propositions that are 'probably true' and advocates for keeping such discussions or determinations open
arXiv:2604.01348v2 Announce Type: replace Abstract: Test-time scaling has emerged as an effective way to improve language models on challenging reasoning tasks. However, most existing methods treat ea
arXiv:2604.17957v1 Announce Type: new Abstract: Process Reward Models (PRMs) have emerged as a powerful tool for providing step-level feedback when evaluating the reasoning of Large Language Models (L
arXiv:2509.26278v4 Announce Type: replace-cross Abstract: Most existing approaches formulate action quality assessment and skill proficiency estimation as discriminative prediction tasks, typically pr
arXiv:2604.17715v1 Announce Type: cross Abstract: Recent advances in large language models for test case generation have improved branch coverage via prompt-engineered mutations. However, they still l
arXiv:2604.18459v1 Announce Type: new Abstract: Visual agents operating in the wild must respond to queries precisely when sufficient evidence first appears in a video stream, a critical capability th
arXiv:2508.10531v3 Announce Type: replace Abstract: Modifications to test-time sampling have emerged as an important extension to diffusion algorithms, with the goal of biasing the generative process
arXiv:2604.17126v1 Announce Type: new Abstract: Vision-language models enable open-vocabulary object grounding through natural language queries, under the implicit assumption that semantically equival
arXiv:2604.17920v1 Announce Type: new Abstract: Synthetic Aperture Radar (SAR) plays a critical role in maritime surveillance, yet deep learning for SAR analysis is limited by the lack of pixel-level
As enterprises race to adopt AI without sacrificing control or flexibility, open-source infrastructure is the stable foundation that enables organizations to modernize while maintaining full digital s
As hybrid and multicloud strategies evolve, a new reality is coming into focus — one where open architectures are increasingly central to operational resilience, sovereignty and choice. The industry’s
arXiv:2604.18444v1 Announce Type: cross Abstract: Zero-shot vision-language models (VLMs) have shown promise for chest radiograph classification, but their performance is often limited by confounding
arXiv:2406.08334v2 Announce Type: replace-cross Abstract: Memory pressure has emerged as a dominant constraint in scaling the training of large language models (LLMs), particularly in resource-constra
arXiv:2604.16889v1 Announce Type: new Abstract: Existing feature-interpretation pipelines typically operate on uniformly sampled units, but only a small fraction of cross-layer transcoder (CLT) featur
arXiv:2510.08047v2 Announce Type: replace-cross Abstract: Robust ASR under domain shift is crucial because real-world systems encounter unseen accents and domains with limited labeled data. Although p
arXiv:2603.04531v2 Announce Type: replace Abstract: Tactile dexterous manipulation is essential to automating complex household tasks, yet learning effective control policies remains a challenge. Whil
Replit announced a feature enabling users to publish applications with a single click, streamlining the deployment process from development to production. This capability reduces friction in the app p
arXiv:2508.02750v2 Announce Type: replace Abstract: This review presents a comprehensive survey and benchmark of pulse shape discrimination (PSD) algorithms for radiation detection, classifying nearly
arXiv:2601.22012v2 Announce Type: replace Abstract: Catastrophic forgetting in continual learning is often measured at the performance or last-layer representation level, overlooking the underlying me
arXiv:2206.14234v3 Announce Type: replace-cross Abstract: In deterministic optimization, it is typically assumed that all problem parameters are fixed and known. In practice, however, some parameters
arXiv:2604.16858v1 Announce Type: new Abstract: Image Quality Assessment (IQA) models are increasingly deployed as perceptual critics to guide generative models and image restoration. This role demand
arXiv:2604.16779v1 Announce Type: cross Abstract: Quantum feature maps offer expressive embeddings for classical learning tasks, and augmenting sparse identification of nonlinear dynamics (SINDy) with
QIMMA (قِمّة) is a quality-focused leaderboard for evaluating Arabic Large Language Models, developed by TIIUAE. The leaderboard benchmarks Arabic LLMs across various performance metrics and tasks to
arXiv:2604.16396v1 Announce Type: new Abstract: Islamic inheritance law (ilm al-mawar{i}th) presents a challenging domain for evaluating large language models' structured reasoning capabilities, requi
arXiv:2602.22639v2 Announce Type: replace Abstract: In structure from motion, quadrifocal tensors capture more information than their pairwise counterparts (essential matrices), yet they have often be
arXiv:2604.16432v1 Announce Type: cross Abstract: AI in applications like screening job applicants had become widespread, and may contribute to unemployment especially among the young. Biases in the A
arXiv:2604.17842v1 Announce Type: new Abstract: LLM benchmarks are increasingly dynamic: instead of containing a fixed set of questions, they define templates and parameters that can generate an effec
AI agents are already too human. Not in the romantic sense, not because they love or fear or dream, but in the more banal and frustrating one. The current implementations keep showing their human orig
arXiv:2604.17321v1 Announce Type: new Abstract: Face morphing attacks pose a substantial risk to the reliability of face recognition systems used in passport issuance, border control, and digital iden
arXiv:2506.07826v2 Announce Type: replace Abstract: Validating autonomous driving (AD) systems requires diverse and safety-critical testing, making photorealistic virtual environments essential. Tradi
arXiv:2504.07415v2 Announce Type: replace-cross Abstract: Automated radiology report generation (RRG) holds potential to reduce the workload of radiologists, and recent advances in multimodal large la
arXiv:2510.04008v5 Announce Type: replace Abstract: Softmax Attention has a quadratic time complexity in sequence length, which becomes prohibitive to run at long contexts, even with highly optimized
arXiv:2604.16310v1 Announce Type: cross Abstract: Evaluating Retrieval-Augmented Generation (RAG) systems using static multi-turn datasets fails to capture the dynamic nature of real-world dialogues.
arXiv:2512.24086v2 Announce Type: replace Abstract: In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which
arXiv:2604.18450v1 Announce Type: cross Abstract: Empirical studies of trained models often report a transient regime in which signal is detectable in a finite gradient descent time window before over
arXiv:2604.16591v1 Announce Type: new Abstract: Large language models (LLMs) sometimes memorize undesirable knowledge, which must be removed after deployment. Prior work on machine unlearning has focu
arXiv:2604.18390v1 Announce Type: new Abstract: In self-supervised learning, self-distilled methods have shown impressive performance, learning representations useful for downstream tasks and even dis
arXiv:2604.17805v1 Announce Type: new Abstract: Pairwise ranking systems based on Maximum Likelihood Estimation (MLE), such as the Bradley-Terry model, are widely used to aggregate preferences from pa