model releases

Measure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Reinforcement Learning in AIoT Systems

arXiv:2607.10309v2 Announce Type: replace Abstract: Reinforcement learning (RL) is commonly employed to enhance the performance of autonomous systems, including the Autonomous Internet of Things (AIoT

Model Releases

Measuring Semantic Abstractness of SAE Features via Nonlocality

DGX agent

arXiv:2608.10537v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have helped uncover mechanistic explanations for LLM behaviours such as reasoning, jailbreaking etc., via understanding the c

model-releasesarxiv-cs-ai

12 Aug 2026

More Accurate, Less Human: Gestalt Grouping in Vision Models

arXiv:2608.10195v1 Announce Type: new Abstract: Human vision organizes what it sees into wholes: same-colored points group into series, similar marks cohere into categories, and shapes complete into r

Multimodal Item Parameter Estimation using Simulated Response Probabilitie

arXiv:2608.10154v1 Announce Type: cross Abstract: We present results from reconstructing multiple-choice model (MCM) and three-parameter logistic (3PL) model curves using a fine-tuned multimodal large

myMediWhisper: Construction of Burmese Medical Speech Corpus and Whisper Fine-Tuning for Clinical Dialogue ASR

arXiv:2608.11036v1 Announce Type: new Abstract: Although Whisper models benefit from large-scale multilingual pre-training, their performance on Burmese medical speech remains limited. This work prese

Navigation Alone Is Not Enough: Evaluating Explanatory Assistive UI Agents

arXiv:2608.09944v1 Announce Type: cross Abstract: Modern web interfaces are increasingly difficult to use with screen readers, particularly when pages update dynamically or hide important structure be

Neural Introspection Gating for Adaptive KV-Cache Reuse in Vision-Language-Action Models

arXiv:2608.10824v1 Announce Type: cross Abstract: Vision-Language-Action(VLA) models map camera images and language instructions directly to motor commands through a single autoregressive transformer.

New Muse-Glimmer-30B SoTA Quants - hopefully a new lineup :)

model-releasesr-localllama

Hey Folks, I've been making quants for a while - recently I took a short break to get into hardcore research (submitted my first EMNLP paper during it!). Along the way, I built up a little arsenal of

No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding

arXiv:2503.05061v3 Announce Type: replace Abstract: Reliable evaluation of large language models (LLMs) is critical as their deployment rapidly expands, particularly in high-stakes domains such as bus

NullEdit: Stealthy Image Protection via VLM Condition Redirection

arXiv:2608.10870v1 Announce Type: new Abstract: Modern image editors combine vision-language models (VLMs) with diffusion transformer backbones to modify a single reference image according to instruct

Nutrition Data Infrastructure for the AI Era: Operationalizing FAIR for Agent-Mediated Research

arXiv:2608.10363v1 Announce Type: new Abstract: AI agents can accelerate nutrition research, but their analyses inherit the identity, semantic, and release ambiguities of the underlying data. We prese

On Solomonoff Induction in Large Language Models and the Limits of Self-Improving: The Singularity Is Not Near Without Symbolic Model Synthesis

arXiv:2601.05280v3 Announce Type: replace-cross Abstract: On the one hand, the question of whether large language models (LLMs) are Solomonoff induction estimators has become an explicit question at t

On the Limitations of Cross-Lingual Consistency in Multilingual Text-to-image Generation

arXiv:2608.11002v1 Announce Type: cross Abstract: Text-to-image (T2I) generation has achieved remarkable progress in recent years. However, existing research has largely focused on English-only settin

Optimal Stopping of Self-Refining Foundation Models

arXiv:2608.10729v1 Announce Type: cross Abstract: Foundation models can improve their outputs through a self-refinement process driven by external feedback. In this process, the model is embedded in a

Optimized Sequential Testing for Binary Ensemble Classifiers

arXiv:2606.15237v1 Announce Type: cross Abstract: Ensemble classifiers are predictive models that combine the results of simpler base models, often by majority vote. A classic example is random forest

Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching

arXiv:2602.13136v2 Announce Type: replace Abstract: Template-free retrosynthesis methods treat the task as black-box sequence generation, limiting learning efficiency, while semi-template approaches r

Path Integral Value Matching for Linear Quadratic Stochastic Optimal Control

arXiv:2608.10777v1 Announce Type: new Abstract: Linear Quadratic Stochastic Optimal Control (LQ-SOC) establishes a fundamental framework for steering noisy dynamical systems and has recently gained re

PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders

arXiv:2608.10985v1 Announce Type: new Abstract: Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infrin

Persistent Recursive Worlds Enable Autonomous Software Evolution

arXiv:2608.10450v1 Announce Type: cross Abstract: Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve conti

Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation

arXiv:2608.10385v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as relevance assessors in information retrieval (IR) evaluation, raising questions about how assess

pi-SUB: A Physics-Informed Synthetic Underwater Benchmark Dataset for Underwater Image Enhancement

arXiv:2608.10589v1 Announce Type: cross Abstract: This paper presents pi-SUB, a physics-informed framework for generating synthetic underwater benchmark datasets that bridges the synthetic-to-real gap

Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference

arXiv:2608.10288v1 Announce Type: cross Abstract: The Large Language Model from Power Law Decoder Representations (PLDR-LLM) and its attention, Power Law Graph Attention (PLGA), replace the fixed bili

Pretrained Optimization Model for Zero-Shot Black Box Optimization

arXiv:2405.03728v3 Announce Type: replace-cross Abstract: Zero-shot optimization involves optimizing a target task that was not seen during training, aiming to provide the optimal solution without or

PRMU: A Corpus-Free Benchmark for Person-Centric Knowledge Unlearning in Multimodal Large Language Models

arXiv:2608.11149v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in storing and recalling rich person-related knowledge, raising incre

ProTAGAD: A Foundation Model for TAG Anomaly Detection with Decoupled Topological and Textual Prototypes

arXiv:2608.10699v1 Announce Type: cross Abstract: Text-Attributed Graphs (TAGs), endowed with abundant textual content along with topological structures, have emerged as a versatile backbone for real-

Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers

arXiv:2608.10989v1 Announce Type: cross Abstract: Token-pruning policies are usually designed for a single recognition pipeline, but pretrained Vision Transformers are reused across tasks with differe

Putting sign language AI into users’ hands

model-releasesgoogle-deepmind

Google DeepMind’s new sign‑language‑to‑text (SL2T) model powers real‑time sign-to-text dictation in Gboard and Live Transcribe on Pixel 11, currently supporting American Sign Language to English. The

Quantum Incremental Learning with Mixed State Prototypes

arXiv:2608.10464v1 Announce Type: new Abstract: Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory c

Qwen 3.8 2.4T is out , no 27b today RIP.

model-releasesr-localllama

i was hoping they would release both today but the big one just dropped now , and it says its been listed since 5 hours ago on huggingface. I guess the real date for 27b is https://modelscope.cn/model

REAP: Relation-Aware Elicitation and Parsing for Closed-Book Knowledge Base Construction from LLMs

arXiv:2608.10963v1 Announce Type: new Abstract: We present the REAP system for the AKBC Shared Task 2026 on constructing knowledge bases from language models in a closed-book setting, subject to a bud

Reasoning Shortcuts and Value Symmetries: What Symmetry Permits, Architecture Realizes, and Optimization Selects

arXiv:2608.10420v1 Announce Type: new Abstract: Reasoning shortcuts are solutions of a neurosymbolic system's rules that produce correct predictions through unintended concepts. A recent framework of

REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems

arXiv:2608.10669v1 Announce Type: new Abstract: Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks. Adversarial inputs can exploit interact

Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation

arXiv:2608.10812v1 Announce Type: cross Abstract: We study reference-free post-training for multilingual machine translation with open large language models. Starting from the supervised-finetuned MiL

Reinforcement Learning-Based Laser Cutting Machine Parameter Optimization

arXiv:2608.10549v1 Announce Type: new Abstract: Achieving high accuracy in laser-based cutting of optical films requires careful tuning of parameters such as focal length and laser power beam, adjuste

ReLTEx: Reliable LLM-based Taxonomy Expansion

arXiv:2608.10970v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in generating semantically relevant concepts and relations, maki

ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization

arXiv:2608.11045v1 Announce Type: cross Abstract: ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (

Rescene: band-limited stochastic forcing turns a frozen neural weather operator into a climate emulator

arXiv:2608.09971v1 Announce Type: cross Abstract: Over the past few years, the rapid development of machine learning (ML) models for weather forecasting has produced deterministic models whose medium-

Rethinking LLM Verification: Evidence Structure, Uncertainty, and Selective Refinement

arXiv:2608.10725v1 Announce Type: new Abstract: Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing models

Rethinking Text-Based Image Retrieval in Specific Domain

arXiv:2608.10524v1 Announce Type: cross Abstract: Driven by the rapid advancement of vision-language representation learning, Text-based Image Retrieval (TBIR) has made notable progress. However, exis

RLMOpt: Adaptive Prompt Optimization via Recursive Language Models

arXiv:2608.10471v1 Announce Type: new Abstract: Prompt optimizers automate the search for prompts that improve language-model performance, but existing methods rely on a predefined optimization proced

SAR2Agri: Learning SAR Intensity Representations for Agricultural Monitoring

arXiv:2608.11142v1 Announce Type: new Abstract: Agricultural monitoring faces unique challenges, arising from the landscape's complex temporal, phenological, and climate dynamics, yet monitoring them

Seeds Before Objectives: Rethinking Evaluation for Low-Resource Garhwali ASR

arXiv:2608.10670v1 Announce Type: new Abstract: At corpus sizes typical of low-resource dialects, single-run comparisons can yield gains that do not replicate. We show this for Garhwali, an under-reso

SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks

arXiv:2608.10144v1 Announce Type: new Abstract: We consider federated parameter efficient fine-tuning of large neural networks with low-rank adaptation (LoRA,~Hu et al. 2022). Combining LoRA with fede

Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Data

arXiv:2607.15606v2 Announce Type: replace Abstract: Synthetic sequential tabular data are increasingly used for privacy-preserving data sharing and data-driven research, but evaluating their fidelity

Significance and Stability Analysis of Gene-Environment Interaction using GxEStat

arXiv:2604.03337v2 Announce Type: replace Abstract: Genotype-environment (GxE) interactions can influence the performance of genotypes across diverse environments, limiting the reliability of genotype

SinD 2.0: A Multi-City UAV Dataset with Semantic Risk Annotations for SOTIF-Oriented Safety Validation at Signalized Intersections

model-releasesarxiv-cs-ro

arXiv:2607.16943v2 Announce Type: replace Abstract: Safety validation at signalized intersections remains a critical bottleneck for the deployment of autonomous driving systems (ADS), as these scenari

Situation Graph Prediction for User Perspective Modeling

arXiv:2602.13319v2 Announce Type: replace Abstract: Perspective-aware AI requires modeling evolving internal states---goals, emotions, contexts---not merely preferences. Progress is limited by a data

SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation

arXiv:2608.10775v1 Announce Type: new Abstract: Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual cont