The Advantage of Fine-Grained Training
arXiv:2509.05130v2 Announce Type: replace Abstract: In classification problems, models are trained to predict a class label based on the input data features. However, class labels are…
Papers 5483 stories
Adaptive Multi-Horizon Reinforcement Learning
arXiv:2607.20656v3 Announce Type: replace Abstract: Effective decision-making in complex and changing environments requires balancing short-term and long-term consequences. In reinforcement learning (RL), this trade-off is typically…
BayesAME: Bayesian Active Model Evaluation
arXiv:2607.27023v1 Announce Type: cross Abstract: Evaluating large generative models across benchmarks is time-consuming and computationally expensive. This drives the need for methods that can estimate full…
Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers
arXiv:2606.21848v2 Announce Type: replace Abstract: Transformer architectures form the foundation of modern natural language processing, making it crucial to address the efficiency and scalability limitations of…
Diagnosing Fine-Grained Inconsistency Classification in Financial Disclosure Text
arXiv:2607.26368v1 Announce Type: new Abstract: Financial disclosures contain numerical claims, temporal statements, entity references, policy commitments, and risk descriptions that may conflict in qualitatively different ways.…
Topology-Constrained Quantized nnUNet for Efficient and Anatomically Accurate 3D Tooth Segmentation
arXiv:2605.04201v2 Announce Type: replace Abstract: We propose a topology-constrained quantized nnUNet framework for efficient and anatomically accurate 3D tooth segmentation, addressing the challenges of spatial distortion…
Mapping small reservoirs across Brazil from 1984 to 2025
arXiv:2606.00675v2 Announce Type: replace Abstract: Water research in Brazil largely overlooks the widespread damming of small streams for agricultural uses including watering cattle, farm-scale hydropower, irrigation,…
Learning Implicit Causal World Models from Multi-Agent Demonstrations
arXiv:2607.26336v1 Announce Type: new Abstract: In model-based reinforcement learning, world models exist as internal simulators, but their training often conflates statistical correlations with causal mechanisms. This…
Universality and Approximation Rates of Graph Neural Networks with Random Features
arXiv:2607.26699v1 Announce Type: cross Abstract: We investigate message-passing graph neural networks with random node features. Random node features are known to enhance the expressiveness of graph…
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
arXiv:2607.27146v1 Announce Type: cross Abstract: Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation. However,…
CustomerSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators
arXiv:2605.08334v2 Announce Type: replace Abstract: We present CustomerSim, an environment and benchmark to evaluate the extent to which Multimodal Large Language Models (MLLMs) can simulate realistic,…
BG-REAL: A Public Real-Data Anchored Benchmark for Background Manipulation Detection and Localization
arXiv:2607.26232v1 Announce Type: new Abstract: Background manipulation is a practical but under-specified image-forensics setting: the manipulated evidence can sit outside the salient foreground object, while many…
Between Gradient and Natural Gradient: A Continuum of LoRA Initializations
arXiv:2607.26247v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) fine-tunes large pretrained models at a fraction of the cost of full fine-tuning, but its performance depends strongly…
Optimal Causal Annotations: An Application to Casenotes in Social Services
arXiv:2502.10605v4 Announce Type: replace-cross Abstract: Problem definition: Estimating causal effects of interventions is central to policy and operations, but outcome data are often missing or costly…
Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents
arXiv:2607.26865v1 Announce Type: new Abstract: LLM agents following the ReAct paradigm are promising enablers of complex multi-step tasks, including multi-hop question answering, code generation, and control…
F(AI)2R: Who Did What, and Who Checked? Verifiable AI Provenance as an Executable Skill
arXiv:2607.25637v1 Announce Type: cross Abstract: F(AI)2R is FAIR research with AI in the loop, twice: an AI-assisted authoring pass and a machine-readable audit pass over every…
ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation
arXiv:2509.22768v3 Announce Type: replace Abstract: We introduce ML2B, the first benchmark for evaluating cross-lingual task comprehension in end-to-end ML pipeline generation by large language models. Despite…
(Im)Paired Programming: Coding Agents Improve Productivity but Harm Understanding
arXiv:2607.26375v1 Announce Type: new Abstract: Coding agents (e.g., Cursor) improve developer productivity by optimizing task completion, but shifting users from writing code to prompting and reviewing…
Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation
arXiv:2606.31088v2 Announce Type: replace Abstract: Conversational talking face generation has recently attracted increasing attention, aiming to synthesize interactive talking videos where characters speak, listen, and respond…
Mitigating Compounding Error via Video Representation Regularization
arXiv:2607.27036v1 Announce Type: cross Abstract: Video diffusion-based world models enable long autoregressive video generation for robotics, autonomous driving and simulation tasks, yet sliding-window autoregressive inference suffers…
RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning
arXiv:2607.26339v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems ground large language models (LLMs) in external corpora, but this reliance exposes them to corpus poisoning: maliciously…
Conformalized Rate-Adaptive Sensing
arXiv:2607.26887v1 Announce Type: new Abstract: Many high-resolution imaging systems face the same fundamental question: when have enough measurements been collected to reconstruct an image accurately? We…
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR) relies on…
StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents
Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectable ones. Elite security researchers…