model releases

A Dataset and Benchmark for Optical Music Recognition of String Quartet Scores

arXiv:2608.10978v1 Announce Type: new Abstract: Optical music recognition (OMR) transcribes music scores into digital formats. While the field has advanced significantly on monophonic and piano-form s

Model Releases

A HamNoSys-Guided Dataset and Baselines for Fine-Grained Isolated Handshape Recognition in Sign Language

DGX agent

arXiv:2608.10588v1 Announce Type: cross Abstract: Purpose: Fine-grained handshape recognition supports computational sign-language transcription, recognition, and translation, but broad, phonetically

model-releasesarxiv-cs-ai

12 Aug 2026

A lower bound for stepsize-based acceleration of gradient descent

arXiv:2608.10418v1 Announce Type: cross Abstract: Recent work has shown that, for smooth convex optimization, plain gradient descent can be accelerated from its textbook convergence rate of O(T^{-1})

A matched-integrator evaluation of Hamiltonian neural networks on pendulum and Kepler dynamics

arXiv:2608.10235v1 Announce Type: new Abstract: Hamiltonian Neural Networks (HNNs) parameterize conservative dynamics through a learned scalar Hamiltonian, providing an architectural prior that is abs

A Quantum Roadmap for Softmax Attention: Exact Born-Rule Analogs for Softmax Attention on the Probability Simplex

arXiv:2608.11173v1 Announce Type: cross Abstract: The attention mechanism forms the foundation of many modern AI models such as the Transformer. In one subclass of problems where attention is used, in

A variational Bayes approach to inference for low-dimensional parameters in high-dimensional linear regression

arXiv:2406.12659v3 Announce Type: replace-cross Abstract: We propose a scalable variational Bayes method for statistical inference for a single or pre-specified low-dimensional subset of the coordinat

Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique

arXiv:2608.10430v1 Announce Type: cross Abstract: Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions

Ahrefs launches AI agent workspace Letaido for marketers and agencies

model-releasessiliconangle

Marketing intelligence company Ahrefs Pte. Ltd. today launched Letaido, an agent-powered marketing workspace built to take over the recurring research, reporting and monitoring work that fills up a ma

AIFS-TC: A simple correction competitive with the operational frontier for tropical cyclone intensity forecasting

arXiv:2608.09959v1 Announce Type: cross Abstract: AI weather models are in the process of revolutionising weather forecasting. While these models have been shown to achieve superior performance to phy

An adaptive and evolvable deep reinforcement learning framework for weather prediction

arXiv:2608.09948v1 Announce Type: cross Abstract: No single AI weather model excels at all variables, pressure levels, and lead times. Rather than building yet another architecture, we reframe the for

Astrolabe: Balancing Load in LLM Serving with Randomized Prediction-Guided Scheduling

arXiv:2508.03611v3 Announce Type: replace-cross Abstract: This paper presents Astrolabe, a randomized prediction-guided scheduler for one-shot request dispatch in multi-instance large language model (

Attention-Path Fragility as an Uncertainty Signal in Large Language Models

arXiv:2608.11138v1 Announce Type: cross Abstract: We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution but also in whether a confident pr

b10369

model-releasesllama-cpp-releases

mtmd: support pocket-tts (#26871) adapt the api text model ok working impl, need verify and clean up mtmd: build the pocket-tts transposed convolutions as GEMM + col2im ggml_conv_transpose_1d has no g

b10373

model-releasesllama-cpp-releases

imatrix.cpp: Move finite check and only check touched experts (#26861) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS In

b10375

model-releasesllama-cpp-releases

chat : tighten bare function parsing for Qwen models (#26793) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)

Bayesian-Agent: Posterior-Guided Skill Evolution Across LLM Agent Harnesses

arXiv:2606.08348v2 Announce Type: replace Abstract: LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these

Behavioral Inference at Scale: The Fundamental Asymmetry Between Motivations and Belief Systems

arXiv:2509.05624v3 Announce Type: replace-cross Abstract: How much information about an agent's underlying values can be recovered from its observable behavior? This question matters for any approach

Benchmarking LLM-Guided Control-Plane Policies for Backend Fault Isolation in HAProxy

arXiv:2608.10532v1 Announce Type: cross Abstract: Static load balancers cannot mitigate a backend that is degraded rather than down: round-robin and least-connections keep routing traffic to a server

Benchmarking Time Series Generation Methods for Privacy-Preserving Forecasting

arXiv:2608.10891v1 Announce Type: new Abstract: Time series forecasting in privacy-sensitive domains often requires training models on released data rather than original observations. Synthetic time s

Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization

arXiv:2608.10798v1 Announce Type: cross Abstract: Most image colorization systems operate in Lab space by predicting chroma (ab) while preserving an input-derived luminance channel (L). While effectiv

Boundary-Seeking Policy Gradient for Safe Reinforcement Learning

arXiv:2608.10204v1 Announce Type: new Abstract: Safe reinforcement learning maximizes reward subject to safety constraints. For Constrained Markov Decision Processes, the linear-programming view over

BPG: Balancing Plasticity and Generalization for Domain Incremental Learning

arXiv:2608.10804v1 Announce Type: cross Abstract: Deep neural networks excel in various tasks but struggle to generalize across evolving data distributions, leading to significant performance degradat

Bridging Severe Cross-Modal Misalignment: End-to-End Visible-Infrared Object Detection via Explicit Feature-Domain Affine Registration

arXiv:2608.10680v1 Announce Type: new Abstract: Visible-infrared object detection relies on complementary RGB and thermal cues, but its performance is often degraded by cross-modal spatial misalignmen

Can Released LLM Vocabularies Support Token-Level Estimation of Hidden Corpora?

arXiv:2608.10690v1 Announce Type: new Abstract: Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus

CapProbe: Evaluating Detailed Image Captions via Full-Scene Dense Question Answering

arXiv:2608.11074v1 Announce Type: new Abstract: Evaluating detailed image captions from Vision-Language Models (VLMs) requires going beyond surface-level semantic similarity. Reference-based metrics (

Chartography: A Benchmark for Professional Chart Understanding

arXiv:2608.10677v1 Announce Type: new Abstract: Professionals across medicine, engineering, finance, manufacturing, and the sciences often make consequential decisions from charts. Existing chart benc

CHORUS: Complementary Experts for High-Coverage Testbench Stimulus Generation

arXiv:2608.10090v1 Announce Type: new Abstract: Large language models (LLMs) have advanced code generation, where executable feedback provides a more reliable learning signal than textual imitation al

Closed-Loop LLM Co-Pilots for Digital Agriculture

arXiv:2608.09949v1 Announce Type: new Abstract: This study evaluates the application of Large Language Models (LLMs) in complex biological systems, evolving from data analysis to autonomous, AI-guided

ComBodied Agents: a New Paradigm of Human-Centric Agentic AI

arXiv:2608.10915v1 Announce Type: new Abstract: After an older adult misses a medication dose, a software agent can send another reminder and an embodied agent can bring the medication. Yet neither ex

Compositional Benchmark Synthesis for Hierarchical Human Action Recognition

arXiv:2608.10765v1 Announce Type: new Abstract: Recognizing human behavior across levels of abstraction, from atomic actions to long-horizon intentions, requires data annotated along a semantic hierar

Cost-Efficient Estimation of General Abilities Across Benchmarks

arXiv:2604.01418v2 Announce Type: replace Abstract: Thousands of diverse benchmarks have been developed to measure the quality of large language models (LLMs). Yet prior work has demonstrated that LLM

Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension

arXiv:2608.10296v1 Announce Type: new Abstract: One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that th

Curate Before You Connect: Identity and Ontology Tagging in a Production Knowledge Graph

arXiv:2608.10644v1 Announce Type: new Abstract: Extraction produces candidate entities and relationships; writing them into a graph is where identity is decided, and identity decisions are destructive

CurveFP: Rational-Radix Logarithmic Datatypes with Closed Products for Language Models

arXiv:2608.10010v1 Announce Type: new Abstract: Low-precision datatypes reduce language-model cost, but most formats optimize scalar fidelity while leaving the arithmetic induced by their products unc

DACRI: Decision-Aware Causal Intervention Ranking for Critical Supply Chains

arXiv:2608.11154v1 Announce Type: new Abstract: Detecting or attributing a supply-chain disruption is not the same as selecting the intervention that maximizes recoverable net value. We present Critic

DashArena: Benchmarking LLMs on Interactive Analytic Dashboard Generation

arXiv:2608.10567v1 Announce Type: new Abstract: Analytic dashboards combine coordinated views and interactions for data exploration and decision-making. Recent models can generate them from data and n

Deciding When to Switch: E-Processes for Adaptive Minimax Training for Generative Adversarial Nets

arXiv:2608.10096v1 Announce Type: cross Abstract: Modern data science increasingly gives rise to hypothesis-testing problems that are not naturally formulated in terms of parameters within prespecifie

DegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation Prediction

arXiv:2608.10595v1 Announce Type: cross Abstract: Proteolysis-targeting chimeras (PROTACs) induce protein degradation by recruiting a target protein to an E3 ubiquitin ligase, making degradation a joi

Derivative Computation in PINNs: Automatic Differentiation, Finite Differences and Beyond

arXiv:2608.11020v1 Announce Type: new Abstract: We systematically investigate finite-difference (FD) derivative computation in Physics-Informed Neural Networks (PINNs) as an alternative to automatic d

Diffract: Spectral View of LLM Domain Adaptation

arXiv:2608.10850v1 Announce Type: new Abstract: We study continual pre-training (CPT) as a mechanism for adapting general-purpose large language models to specialized domains: mathematics, instruction

DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation

arXiv:2608.10636v1 Announce Type: cross Abstract: Visual document retrieval (VDR) is dominated by multi-billion-parameter models that are slow to index at full corpus scale and expensive to serve. Pri

Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness

arXiv:2608.10008v1 Announce Type: cross Abstract: LLM recommenders for top-K item suggestion regularly emit titles outside the target catalog. Prior audits measure this as a binary out-of-domain rate;

DreamOmni3: Scribble-based Editing and Generation

arXiv:2512.22525v2 Announce Type: replace Abstract: Recently unified generation and editing models have achieved remarkable success with their impressive performance. These models rely mainly on text

DriveVLA-M0: Failure-Aware Memory Augmentation for Autonomous Driving

arXiv:2608.10413v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for end-to-end autonomous driving by enabling unified reasoning across

DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?

arXiv:2608.10366v1 Announce Type: new Abstract: Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coor

E^3mo-Bench: A Scalable Benchmark for Multimodal Evoked and Expressed Emotion Understanding via Bayesian Pairwise Alignment

arXiv:2608.10796v1 Announce Type: new Abstract: Understanding both expressed and evoked emotions is critical for multimodal large language models (MLLMs) to achieve comprehensive affect-aware interact

Edge Phoneme Recognition for Children's Speech through Age-Aware Training

arXiv:2608.10206v1 Announce Type: new Abstract: Detecting phonemes from children's speech has historically been difficult due to the scarcity of training data, and unique characteristics of children's

Efficient Reinforcement Learning for Long-Horizon Tool-Use Agentic Tasks

arXiv:2608.10357v1 Announce Type: cross Abstract: Long-horizon tool-using agents must reason over user goals, domain policies, tool calls, simulator state, and delayed verifiable rewards. Reinforcemen