Search: “model-releases”

Ambig-DS: A Benchmark for Task-Framing Ambiguity in Data-Science Agents

arXiv:2605.09698v1 Announce Type: new Abstract: As data-science agents shift from co-pilots to auto-pilots, silent misframing becomes a critical failure mode. Agents quietly commit to plausible but un

Model Releases

An Annotation Scheme and Classifier for Personal Facts in Dialogue

DGX agent

arXiv:2605.10339v1 Announce Type: new Abstract: The advancement of Large Language Models (LLMs) has enabled their application in personalized dialogue systems. We present an extended annotation scheme

model-releasesarxiv-cs-cl

12 May 2026

An Empirical Study of Multi-Agent Collaboration for Automated Research

arXiv:2603.29632v2 Announce Type: replace-cross Abstract: As AI agents evolve, the community is rapidly shifting from single Large Language Models (LLMs) to Multi-Agent Systems (MAS) to overcome cogni

AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation

arXiv:2605.10397v1 Announce Type: cross Abstract: Visual anomaly detection (VAD) is crucial in many real-world fields, such as industrial inspection, medical imaging, infrastructure monitoring, and re

Anthropic announces 12 Claude plugins for the legal sector, including a 'commercial counsel' tool for reviewing vendor agreements and a bar exam study tool (Rachel Metz/Bloomberg)

Rachel Metz / Bloomberg: Anthropic announces 12 Claude plugins for the legal sector, including a “commercial counsel” tool for reviewing vendor agreements and a bar exam study tool — Anthropic PBC is

model-releasestechmeme

AnyDepth-DETR/-YOLO: Any-depth object detection with a single network

arXiv:2605.09407v1 Announce Type: new Abstract: Modern object detectors are static, fixed-depth networks optimized for a single operating point, requiring separate models for different deployment scen

Arcane: An Assertion Reduction Framework through Semantic Clustering and MCTS-Guided Rule Exploring

arXiv:2605.10107v1 Announce Type: new Abstract: Assertion-based Verification (ABV) is essential for ensuring that hardware designs conform to their intended specifications. However, existing automated

Architecture, Not Scale: Circuit Localization in Large Language Models

arXiv:2605.08853v1 Announce Type: new Abstract: Mechanistic interpretability assumes that circuit analysis becomes harder as models scale. We challenge this assumption by showing that the attention ar

Are vision-language models ready to zero-shot replace supervised classification models in agriculture?

arXiv:2512.15977v3 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly proposed as general-purpose solutions for visual recognition tasks, yet their reliability for agricul

Artificial Intelligence in Number Theory: LLMs for Algorithm Generation and Ensemble Methods for Conjecture Verification

arXiv:2504.19451v3 Announce Type: cross Abstract: This paper presents two concrete applications of Artificial Intelligence to algorithmic and analytic number theory. Recent benchmarks of large languag

AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents

arXiv:2605.10876v1 Announce Type: cross Abstract: Recent advances in machine learning and large-scale biological data collections have revived the prospect of building a virtual cell, a computational

AssemPlanner: A Multi-Agent Based Task Planning Framework for Flexible Assembly System

model-releasesarxiv-cs-ro

arXiv:2605.08831v1 Announce Type: new Abstract: In flexible assembly systems, existing task planning methods require a time-consuming configuration process by multiple experts to establish a productio

ASTRA-QA: A Benchmark for Abstract Question Answering over Documents

arXiv:2605.10168v1 Announce Type: new Abstract: Document-based question answering (QA) increasingly includes abstract questions that require synthesizing scattered information from long documents or a

Attention Grounded Enhancement for Visual Document Retrieval

arXiv:2511.13415v2 Announce Type: replace-cross Abstract: Visual document retrieval requires understanding heterogeneous and multi-modal content to satisfy implicit information needs. Recent advances

AUHead: Realistic Emotional Talking Head Generation via Action Units Control

arXiv:2602.09534v2 Announce Type: replace Abstract: Realistic talking-head video generation is critical for virtual avatars, film production, and interactive systems. Current methods struggle with nua

Automated Approach for Solving Infinite-state Polynomial Reachability Games

arXiv:2605.10169v1 Announce Type: new Abstract: Reachability games are two-player games played on a graph, where the objective of exttt{REACH} player is to reach the target set whereas the objective o

BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation

arXiv:2605.10845v1 Announce Type: cross Abstract: As global cross-lingual communication intensifies, language barriers in visually rich documents such as PDFs remain a practical bottleneck. Existing d

BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight Quantization

arXiv:2605.10655v1 Announce Type: new Abstract: Trellis-coded quantization sets the current 2-bit post-training frontier for LLMs (QTIP), but pushing below the PTQ ceiling requires quantization-aware

BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data

arXiv:2605.10867v1 Announce Type: cross Abstract: Continuous authentication in high-stakes digital environments requires datasets with fine-grained behavioral signals under realistic cognitive and mot

BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD

arXiv:2605.10865v1 Announce Type: new Abstract: Industrial Computer-Aided Design (CAD) code generation requires models to produce executable parametric programs from visual or textual inputs. Beyond r

BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognition

arXiv:2605.08296v1 Announce Type: new Abstract: Human Activity Recognition (HAR) from wearable sensors supports broad healthcare and behavior science applications. However, data heterogeneity and the

Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials

arXiv:2605.08988v1 Announce Type: cross Abstract: Machine Learning Interatomic Potentials play a fundamental role in computational chemistry and materials science, enabling applications from molecular

Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing

arXiv:2605.10146v1 Announce Type: new Abstract: Large language models (LLMs) increasingly rely on knowledge editing to support knowledge-intensive reasoning, but this flexibility also introduces criti

Benchmarking Sensor-Fault Robustness in Forecasting

arXiv:2605.10822v1 Announce Type: new Abstract: Cyber-physical system (CPS) forecasting models depend on sensor streams with noisy, biased, missing, or temporally misaligned readings, yet standard for

Benchmarking Transformer and xLSTM for Time-Series Forecasting of Heat Consumption

arXiv:2605.09722v1 Announce Type: new Abstract: Obtaining an accurate short-term forecasting for heat demand is an essential part of operating district heating networks cost-efficient and reliable. He

@BereznevKi20669 @ggerganov Yes I believe the real llama.cpp revolution is yet to happen at its full scale. As computers will have more RAM …

model-releasesgeorgi-gerganov--x

@BereznevKi20669 @ggerganov Yes I believe the real llama.cpp revolution is yet to happen at its full scale. As computers will have more RAM and models will improve, and *if* China will continue shippi

Beyond Accuracy: Evaluating Strategy Diversity in LLM Mathematical Reasoning

arXiv:2605.09292v1 Announce Type: new Abstract: Large language models now achieve high final-answer accuracy on mathematical reasoning benchmarks, but accuracy alone does not capture reasoning flexibi

Beyond Isolation: A Unified Benchmark for General-Purpose Navigation

model-releasesarxiv-cs-ro

arXiv:2605.09441v1 Announce Type: new Abstract: The pursuit of general-purpose embodied agents is hindered by fragmented evaluation protocols that isolate navigation skills and fixate on specific robo

Beyond Language: Format-Agnostic Reasoning Subspaces in Large Language Models

arXiv:2605.09496v1 Announce Type: new Abstract: Large language models represent the same reasoning in vastly different surface forms -- English prose, Python code, mathematical notation -- yet whether

Beyond Local Edits: Embedding-Virtualized Knowledge for Broader Evaluation and Preservation of Model Editing

arXiv:2602.01977v2 Announce Type: replace Abstract: Knowledge editing methods for large language models are commonly evaluated using predefined benchmarks that assess edited facts together with a limi

Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers

arXiv:2605.10901v1 Announce Type: new Abstract: Guardrail Classifiers defend production language models against harmful behavior, but although results seem promising in testing, they provide no formal

Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving

model-releasesarxiv-cs-ro

arXiv:2605.10034v1 Announce Type: new Abstract: Recent Autonomous Driving (AD) works such as GigaFlow and PufferDrive have unlocked Reinforcement Learning (RL) at scale as a training strategy for driv

Beyond source code: The files AI coding agents trust — and attackers exploit

model-releasesgoogle-cloud-ai

As AI coding agents become deeply embedded in developer workflows, defenders must evolve their definition of malicious files and rethink how to protect against them. Autonomous AI agents operate acros

Beyond the All-in-One Agent: Benchmarking Role-Specialized Multi-Agent Collaboration in Enterprise Workflows

arXiv:2605.08761v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly expected to operate in enterprise environments, where work is distributed across specialized roles,

Beyond the False Trade-off: Adaptive EWC for Stealthy and Generalizable T2I Backdoors

arXiv:2605.08280v1 Announce Type: cross Abstract: Preserving model fidelity is essential for stealthy text-to-image (T2I) backdoor attacks. Existing methods such as Learning without Forgetting (LwF) r

Beyond the Singular: Revealing the Value of Multiple Generations in Benchmark Evaluation

arXiv:2502.08943v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated significant utility in real-world applications, exhibiting impressive capabilities in natural l

Beyond Toy Benchmarks: A Systematic Evaluation of OOD Detection Methods For Plant Pathology Classification

arXiv:2605.08618v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection is essential for reliable deployment of deep learning systems, yet the majority of existing methods are evaluated on

BGG: Bridging the Geometric Gap between Cross-View images by Vision Foundation Model Adaptation for Geo-Localization

arXiv:2605.10345v1 Announce Type: new Abstract: Geometric differences between cross-view images, such as drone and satellite views, significantly increase the challenge of Cross-View Geo-Localization

BiAxisAudit: A Novel Framework to Evaluate LLM Bias Across Prompt Sensitivity and Response-Layer Divergence

arXiv:2605.09041v1 Announce Type: new Abstract: Bias audits of large language models now operate within governance frameworks such as the EU AI Act, making benchmark reliability a security concern in

Bilinear autoencoders find interpretable manifolds

arXiv:2605.08891v1 Announce Type: new Abstract: Sparse autoencoders have become a standard tool for uncovering interpretable latent representations in neural networks. Yet salient concepts often span

BoostLLM: Boosting-inspired LLM Fine-tuning for Few-shot Tabular Classification

arXiv:2605.06117v2 Announce Type: replace Abstract: Large language models (LLMs) have recently been adapted to tabular prediction by serializing structured features into natural language, but their pe

Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning

arXiv:2605.08271v1 Announce Type: cross Abstract: Understanding ultra-long videos such as egocentric recordings, live streams, or surveillance footage spanning days to weeks, remains a challenge. For

Bridging Spectral Operator Learning and U-Net Hierarchies: SpectraNet for Stable Autoregressive PDE Surrogates

arXiv:2605.09096v1 Announce Type: new Abstract: Neural operators for time-dependent PDEs face a structural tension: spectral architectures (FNO and descendants) inherit exponential rollout-error growt

Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models

arXiv:2605.08404v1 Announce Type: cross Abstract: This work investigates the use of large language models (LLMs) for tasks in smart cities. The core idea is to leverage remote sensing imagery to chara

bViT: Investigating Single-Block Recurrence in Vision Transformers for Image Recognition

arXiv:2605.10661v1 Announce Type: cross Abstract: Vision Transformers (ViTs) are built by stacking independently parameterized blocks, but it remains unclear how much of this depth requires layer spec

Byte-Exact Deduplication in Retrieval-Augmented Generation: A Three-Regime Empirical Analysis Across Public Benchmarks

arXiv:2605.09611v1 Announce Type: new Abstract: This preprint presents an empirical analysis of byte-exact chunk-level deduplication in Retrieval-Augmented Generation (RAG) pipelines. We measure conte

C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving

arXiv:2605.10744v1 Announce Type: new Abstract: Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing

CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation

arXiv:2605.10873v1 Announce Type: cross Abstract: Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existin