Skip to content

Papers 5629 stories

arXiv cs.LG Papers

Local Label-Informed Feature Transfer for Generating Ground-Truth Medical Images: A Comparison of GAN- and Diffusion-Based Approaches

arXiv:2607.18882v1 Announce Type: cross Abstract: Validating Explainable Artificial Intelligence (XAI) methods in medical imaging requires ground-truth data with known locations of informative features. However, current approaches…

arXiv cs.LG Papers

Can Interpretation Predict Behavior on Unseen Data?

arXiv:2507.06445v3 Announce Type: replace Abstract: Interpretability research often predicts model responses to targeted mechanistic interventions. But can we predict responses to unseen input data? We propose…

arXiv stat.ML Papers

Low-Rank Evolutionary Deep Neural Networks via Adaptive Tangent-Space Reduction

arXiv:2509.16395v2 Announce Type: replace Abstract: Evolutionary deep neural networks (EDNNs) solve time-dependent partial differential equations by evolving the neural-network parameters sequentially in time through a local…

arXiv cs.AI Papers

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads

arXiv:2607.18253v1 Announce Type: new Abstract: Modern language query routers improve inference efficiency by assigning each query to a model that balances response quality and monetary cost.…

arXiv cs.CL Papers

HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks

arXiv:2607.18867v1 Announce Type: cross Abstract: Large language models leak parametric knowledge of realized outcomes into historical financial decision tasks. Existence is settled; what users lack is…

arXiv cs.CL Papers

Estimating near-verbatim extraction risk in language models with decoding-constrained beam search

arXiv:2603.24917v2 Announce Type: replace Abstract: Recent work shows that standard greedy-decoding extraction methods for quantifying memorization in LLMs miss how extraction risk varies across sequences. Probabilistic…

arXiv cs.CV Papers

Text-conditioned Segmentation for Tomato Phenotyping via Procedural Synthetic Data

arXiv:2607.18576v1 Announce Type: new Abstract: Vision-based automation is an excellent candidate for reducing manual labor in greenhouse crop production and phenotyping. However, progress is constrained by…

arXiv cs.LG Papers

Preference-Conditioned Multi-Objective Reinforcement Learning for Runtime-Tunable Transit Signal Priority

arXiv:2607.18286v1 Announce Type: new Abstract: Transit signal priority (TSP) requires balancing competing objectives: reducing bus delay while limiting adverse impacts on non-bus traffic and avoiding extreme…

arXiv cs.LG Papers

Reliability Scales Inversely: Bigger Models Compound Mistakes Faster via a Hidden Auto-Regressive Risk Regime

arXiv:2607.18292v1 Announce Type: new Abstract: As language models scale, answers start truer but degrade faster: scaling buys capability but erodes reliability. The knowledge-gap account - more…

arXiv stat.ML Papers

Fundamental limits of distributed multiclass classification from simple binary decisions

arXiv:2607.19334v1 Announce Type: new Abstract: We consider the problem of constructing a $K$-class classifier from the combination of $O(log K)$ simple binary classifiers -- this is…

arXiv cs.AI Papers

SR-Agent: An Experience-Driven Agentic Framework for Post-Ranking Strategy Refinement in E-Commerce Recommendation

arXiv:2607.17719v2 Announce Type: replace Abstract: User experience is a first-class objective in industrial e-commerce recommender systems (RS). Post-ranking strategies, which govern diversity, similarity, and exposure over…

arXiv cs.AI Papers

Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems

arXiv:2603.07473v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) is an open and standardized interface that enables large language models (LLMs) to interact with external…

arXiv cs.CL Papers

Computational models of pragmatic reasoning with flexible generation of meaning and expression alternatives

arXiv:2607.18443v1 Announce Type: new Abstract: Pragmatic language use requires reasoning about alternatives: the alternative expressions a speaker might have chosen, or the alternative interpretations a listener…

arXiv cs.CL Papers

Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning

arXiv:2607.18615v1 Announce Type: new Abstract: Machine unlearning for vision-language models (VLMs) remains underexplored. Unlike language models, VLMs combine a language backbone with visual components, which makes…

arXiv cs.CV Papers

PC-Seg: Progressive Cross-View Consistency for 3D OCT Segmentation from Sparse 2D Annotations

arXiv:2607.17718v2 Announce Type: replace Abstract: Volumetric segmentation of optical coherence tomography (OCT) images is essential for diagnosing ocular diseases but requires labor-intensive voxel-wise annotations. While semi-supervised…

arXiv cs.LG Papers

BearingNAS: Obtaining In-Sensor Intelligent Fault Diagnosis Systems for Bearings Using a Laptop

arXiv:2607.18287v1 Announce Type: new Abstract: This paper introduces BearingNAS, a Hardware-Aware Neural Architecture Search (HW-NAS) framework designed to shift the intelligence directly onto the sensor die…

arXiv cs.LG Papers

Information Theoretic Bayesian Optimization over the Probability Simplex

arXiv:2603.09793v2 Announce Type: replace Abstract: Bayesian optimization is a data-efficient technique that has been shown to be extremely powerful to optimize expensive, black-box, and possibly noisy…

arXiv stat.ML Papers

PAC–Bayes Bounds on Quotient Parameter Spaces: Geometry-induced Implicit-Bias Priors

arXiv:2607.18422v1 Announce Type: cross Abstract: Overparameterized models often have continuous parameter symmetries, so different parameters define the same predictor. We show that PAC--Bayesian analysis should be…

arXiv cs.AI Papers

Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning

arXiv:2607.19345v1 Announce Type: cross Abstract: Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, and extending them to long-context settings…

arXiv cs.AI Papers

Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR

arXiv:2607.18254v1 Announce Type: new Abstract: Multi-Level Intermediate Representation (MLIR) underlies modern ML compiler infrastructure (TensorFlow, JAX/StableHLO, PyTorch Inductor, IREE), yet appears only in trace amounts in…

arXiv cs.CL Papers

Using Fine-Tuned LLMs to Identify Indicators of Vulnerability in UK Police Incident Logs

arXiv:2607.18446v1 Announce Type: new Abstract: Purpose: Understanding how much of routine policing involves vulnerable people could inform resourcing, training, and multi-agency response, yet administrative data provide…

arXiv cs.CV Papers

OF$^3$GS: On-the-Fly Feed-Forward 3D Gaussian Splatting from Unposed Images

arXiv:2606.03254v2 Announce Type: replace Abstract: Feed-forward 3D Gaussian Splatting (3DGS) enables efficient and high-fidelity novel view synthesis (NVS) from offline image sequences. However, achieving on-the-fly NVS…

arXiv cs.CV Papers

Attention Without Grounding: Causal Evaluation of Visual Explanations in Medical VLMs

arXiv:2607.18577v1 Announce Type: new Abstract: Attention and saliency heatmaps are widely used to explain medical Vision-Language Model (VLM) outputs on chest X-rays, yet whether they truly…

arXiv cs.LG Papers

Compressing What Matters: Neuron Importance Meets Data-Aware Low Rank Approximation for Language Model Compression

arXiv:2607.18284v1 Announce Type: new Abstract: To excel at their domain large language models are comprised of billions of parameters. Yet this comes at the cost of…