Search: “models”

PLSQLBench: Benchmarking LLM Systems for Executable Procedural Database Programming

arXiv:2608.15931v1 Announce Type: new Abstract: We present PLSQLBench, to our knowledge the first benchmark for evaluating whether LLMs can write executable PL/SQL programs, with correctness measured

Safety

Pointer Networks with Q-Learning for Combinatorial Optimization

DGX agent

arXiv:2311.02629v5 Announce Type: replace Abstract: We introduce the Pointer Q-Network (PQN), a hybrid neural architecture that integrates model-free Q-value policy approximation with Pointer Networks

safetyarxiv-cs-lg

18 Aug 2026

PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection

model-releasesarxiv-cs-cv

arXiv:2608.15802v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection remains challenging for image classifiers, especially when near-OOD samples lie close to in-distribution (ID) class

Qwen 27B is the 'DeepSeek moment' for open source. It matches the closed-source state-of-the-art from just a few months ago and runs on an R…

model-releasesclem-delangue--x

Qwen 27B is the 'DeepSeek moment' for open source. It matches the closed-source state-of-the-art from just a few months ago and runs on an RTX 5090. Without exaggeration, it’s a game changer. let that

R^3-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets

arXiv:2608.16033v1 Announce Type: new Abstract: In cognitive science, resource rationality asks how an agent should allocate limited computation to maximize expected value. Most reasoning and agent be

safetyarxiv-cs-cl

RamseyGadgets: A Graph Construction Dataset for LLMs

arXiv:2608.14999v1 Announce Type: cross Abstract: Constructing special graphs is an important task within graph theory and computer science. Many popular graph constructions are the result of a compre

RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution

arXiv:2608.15924v1 Announce Type: new Abstract: Cloud-side inference gives imitation-learning policies access to greater computational resources, but communication and computation delays can degrade c

Readiness Barrier Functions: Forward-Invariant Control Authority for Overactuated Multirotor Allocation

arXiv:2608.16335v1 Announce Type: new Abstract: Allocation schemes that greedily maximize a readiness metric over the actuator fiber bundle of an overactuated multirotor produce commands that jump bet

REFLEX: Reflexive Equilibrium Fixed-point Learning for Endogenous eXchanges

arXiv:2608.16155v1 Announce Type: new Abstract: In over-the-counter corporate bond markets, dealers compete for client trades by quoting bid and ask prices. Tighter quotes attract more business, but a

safetyarxiv-cs-lg

Resource-Efficient QUBO Formulation for Anchored Currency Arbitrage

model-releasesarxiv-cs-lg

arXiv:2608.15889v1 Announce Type: cross Abstract: Currency arbitrage (CA) involves trading currencies in cycles to exploit discrepancies in market valuations. Quadratic unconstrained binary optimizati

Retrieval-guided Twin Fusion with Similarity-aware Contrast for Molecule-Text Alignment

model-releasesarxiv-cs-lg

arXiv:2608.16005v1 Announce Type: new Abstract: This paper studies the problem of molecule-text alignment, which aims to project molecules and their textual descriptions into a joint latent space for

Robot-Body-Aware Traversal Risk Graph Planning for Wheeled-Legged Robots in Complex Terrain

arXiv:2608.16433v1 Announce Type: new Abstract: Traversal Risk Graphs (TRGs) provide a compact, terrain-aware representation for global navigation, but native TRG costs are computed over circular node

Robust structure from motion for aerial-ground images via detector-free feature matching and multi-view track refinement

arXiv:2608.15251v1 Announce Type: new Abstract: Integrated 3D reconstruction from aerial-ground images is essential for generating high-precision urban 3D models, yet severe variations in viewpoint, s

safetyarxiv-cs-cv

Local Ai

RouteTS: Frequency-Time Routing for Time Series Forecasting

arXiv:2608.14682v1 Announce Type: new Abstract: Real-world time series inherently intertwine global periodic structures with localized non-stationary variations. Existing approaches process these hete

local-aiarxiv-cs-lg

SCALE: State-Calibrated Latent Embeddings for JEPA Planning in the Right Geometry

arXiv:2608.16287v1 Announce Type: new Abstract: Joint-embedding predictive world models plan by scoring predicted terminal embeddings against a goal embedding using a cost defined on the representatio

safetyarxiv-cs-lg

Second-Order Policy Effects as State Transitions: A Source-Linked Benchmark for Policy Simulation

arXiv:2608.15101v1 Announce Type: new Abstract: Policy evaluation often estimates direct benefits and costs while treating the institutional environment as fixed. In practice, a policy changes the sys

SEER: Long-Context Reasoning via Selective Visual-Text Compression

arXiv:2608.15962v1 Announce Type: new Abstract: Long-context reasoning remains computationally expensive for large language models due to the quadratic complexity of attention over text tokens. Visual

researcharxiv-cs-cl

Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors

arXiv:2608.16707v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as decision-making agents in settings that require sophisticated environmental exploration. How

safetyarxiv-cs-ai

Agents

Semantic Uncertainty-Guided Orchestration in Hierarchical Multi-Agent Systems

arXiv:2608.14707v1 Announce Type: new Abstract: As large language model (LLM)-based multi-agent systems become increasingly capable, coordinating agents under uncertainty becomes a fundamental challen

agentsarxiv-cs-ai

Shape Operator PCA: Curvature-Aware Projections for Geometric Machine Learning

arXiv:2608.15313v1 Announce Type: cross Abstract: In this paper, we propose SHOPCA (Shape Operator-based Principal Component Analysis), a novel method for unsupervised metric learning and dimensionali

SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection

arXiv:2608.16338v1 Announce Type: cross Abstract: Video lane detection requires predictions that remain stable across frames, yet severe vehicle occlusions can break temporal cues. In streaming recurr

safetyarxiv-cs-ai

Skill2Query: Exploiting Skill Structure to Generate Pseudo-Queries for Agent Skill Retrieval

arXiv:2608.16071v1 Announce Type: new Abstract: Pseudo-query generation can alleviate the supervision bottleneck for agent skill retrieval, but existing document-level approaches typically leave the r

Local Ai

Solvable Sokoban Without a Solver via Diffusion

arXiv:2608.15958v1 Announce Type: new Abstract: Deciding whether a Sokoban puzzle is solvable is PSPACE-complete (Culberson, 1997): solutions can be exponentially long and there is no short certificat

local-aiarxiv-cs-ai

Spectral Saliency for Machine Unlearning

arXiv:2608.15548v1 Announce Type: cross Abstract: Machine unlearning (MU) aims to remove the influence of specific training data while preserving model utility. As the name suggests, MU can be viewed

STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment

arXiv:2608.16553v1 Announce Type: new Abstract: Multi-preference alignment is often framed as scalarization: combine reward dimensions, then optimize. This leaves a temporal decision underspecified: w

StructRL: Structured Action-Space Exploration for Flow-Based VLAs

arXiv:2608.15139v1 Announce Type: new Abstract: Flow-based Vision-Language-Action (VLA) models are now widely used for continuous robotic manipulation, and online reinforcement learning (RL) is emergi

safetyarxiv-cs-ro

Tutorials

Supervising the Path to Fine Scales: GalerkinFlow for Scientific-Field and Image Super-Resolution

arXiv:2608.16546v1 Announce Type: new Abstract: Most super-resolution models learn from paired data by supervising only the final high-resolution output. This provides little control over how the pred

tutorialsarxiv-cs-cv

Tac4Loco: Learning Spatiotemporal Plantar Pressure Representations for Humanoid Locomotion

arXiv:2608.15766v1 Announce Type: new Abstract: Humanoid robots are expected to traverse complex terrains, where the plantar support may vary dramatically due to foot placement errors, ground properti

The Benchmark Trap: Structures of Power and Injustice in AI Evaluations

arXiv:2608.15326v1 Announce Type: new Abstract: Artificial intelligence (AI) benchmarks are not neutral tools of evaluation but socio-technical artefacts that shape competition, power, and research pr

The Limits of Binding in Dual Encoders

arXiv:2608.15971v1 Announce Type: cross Abstract: Dual-encoder models such as CLIP score an image-caption pair by a single inner product of two independently computed unit vectors, and fail at binding

researcharxiv-cs-cl

The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context

arXiv:2608.14838v1 Announce Type: cross Abstract: Retrieval components for code assistants are tuned against retrieval metrics: a configuration that raises recall@k is adopted, and downstream task suc

The Right Prior for the Right Deformation: Rethinking Continuous Deformable Image Registration

arXiv:2608.16146v1 Announce Type: new Abstract: Deformable image registration models implicitly encode deformation priors through their parametrization and optimization. In this work, we conduct a val

researcharxiv-cs-cv

Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation

arXiv:2502.13207v4 Announce Type: replace-cross Abstract: Despite the increasing use of large language models for creative tasks, their outputs often lack diversity. Common solutions, such as sampling

Tutorials

Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs

arXiv:2603.06697v2 Announce Type: replace-cross Abstract: Vision--language models (VLMs) process images as visual tokens, yet their intermediate reasoning is often carried out in text, which can be su

tutorialsarxiv-cs-ai

TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability

arXiv:2405.17678v2 Announce Type: replace-cross Abstract: Achieving zero-shot adversarial robustness without sacrificing generalization remains challenging for foundation models such as CLIP, especial

Token Distribution versus Data Volume: Domain Balancing in Multi-Domain Meeting Summarisation

arXiv:2608.15935v1 Announce Type: new Abstract: Jointly fine-tuning an LLM on meeting-summarisation corpora of widely varying size raises a question that prior work leaves confounded: when a domain-ba

Towards a theory of inference-time alignment with unknown rewards

arXiv:2608.15402v1 Announce Type: new Abstract: Generative model alignment has received broad interest, and significant progress has been made in supervised fine-tuning and inference-time computation.

safetyarxiv-cs-lg

Tutorials

Towards Reasonable Molecular Structure Elucidation from Infrared Spectroscopy with Chemical Feedback

arXiv:2608.16082v1 Announce Type: new Abstract: Infrared (IR) spectra provide characteristic signals of molecular structure, which are often interpreted by experts via functional-group identification

tutorialsarxiv-cs-lg

Towards Zero-Shot Domain Generalization for ID Cards Presentation Attack Detection

model-releasesarxiv-cs-cv

arXiv:2608.16591v1 Announce Type: new Abstract: Presentation-Attack Detection (PAD) for national ID cards is limited by the lack of publicly available genuine samples, making it difficult for systems

Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions

model-releasesarxiv-cs-lg

arXiv:2608.14642v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents trained on a single reward signal exploit the gap between the designed reward and the intended behavior. This is part

Try Grok 4.6! Grok 4.7, which is a major upgrade, is coming soon.

model-releaseselon-musk--x

Try Grok 4.6! Grok 4.7, which is a major upgrade, is coming soon. Grok 4.6 is up to 5× cheaper than GPT-5.6 Sol while delivering the exact same performance on this benchmark Both score 61 on Artificia

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations

arXiv:2608.15930v1 Announce Type: new Abstract: Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliab

Understanding and Stabilizing Deep Q-Learning via Controlled Bootstrapping and Regulated Value Dynamics

arXiv:2608.16182v1 Announce Type: cross Abstract: Deep Q-learning (DQL) has achieved remarkable empirical success in reinforcement learning, yet its training process remains notoriously unstable. Exis

Unraveling the Size Determination Mechanism of Nanocrystal Synthesis via Interpretable Neural Networks

arXiv:2608.14734v1 Announce Type: cross Abstract: Deep learning models of nanocrystal synthesis enable the prediction of size and shape by encoding precursors and reaction conditions. However, their b

Unsupervised Anomaly Detection for Image Dataset Quality Assurance in Multi-Center Breast MRI

arXiv:2608.16725v1 Announce Type: cross Abstract: Corrupted, inconsistent, or anomalous data silently threatens the safety and reliability of medical AI. Despite growing regulatory recognition of data

Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays

arXiv:2608.14639v1 Announce Type: cross Abstract: Per-field accept/review with selective risk at most alpha -- accept a field only if the error rate among accepted fields is controlled -- is the trust

Validation-Frontier Representation Selection under Constrained Observation

arXiv:2608.15095v1 Announce Type: new Abstract: AI systems deployed outside clean benchmark settings often rely on observations that are incomplete, unstable, costly, or degraded by monitoring failure

Walk Before You Run: The Importance of Data Exploration for Data Analysis Agents

arXiv:2608.16045v1 Announce Type: cross Abstract: LLM-based data-analysis tools are increasingly used to help users analyze messy spreadsheets and workbooks, from answering questions over uploaded fil