model releases

A look at DeepSeek's model optimization to reduce HBM use, potentially enabling domestic memory, ASIC, and CPU makers to create a Chinese AI hardware ecosystem (@bookwormengr)

@bookwormengr: A look at DeepSeek's model optimization to reduce HBM use, potentially enabling domestic memory, ASIC, and CPU makers to create a Chinese AI hardware ecosystem — Have you ever wondered,

model-releasestechmeme

A measurement substrate for agentic Kubernetes operations: Methodology and a case study in retrieval-compounding falsification

arXiv:2605.23058v1 Announce Type: cross Abstract: Empirical claims about autonomous Kubernetes operations agents are largely unfalsifiable. Published work reports observational results without control

A Reproducible Universal Dependencies-Style Pipeline for Katharevousa Greek Parliamentary Text

arXiv:2605.22978v1 Announce Type: new Abstract: Katharevousa Greek remains poorly served by contemporary NLP pipelines despite its importance for legal, administrative, and parliamentary archives. We

A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning

arXiv:2602.13249v2 Announce Type: replace-cross Abstract: Small-molecule foundation models are typically pretrained on standalone molecular data, unlike vision and language models that often benefit f

Agentic Proving for Program Verification

arXiv:2605.23772v1 Announce Type: new Abstract: Agentic systems have recently emerged as state-of-the-art approaches for automated theorem proving in formal mathematics. To assess how far these capabi

Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models

arXiv:2605.22896v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for robotic manipulation by leveraging pre-trained vision-language representa

AI Evaluation Should Require Standardized Item-Level Data Releases

arXiv:2604.03244v2 Announce Type: replace Abstract: This position paper argues that standardized item-level benchmark data should become the default infrastructure for AI evaluation. Current evaluatio

An open source model has returned to #1 on the 3D Design leaderboard by Design Arena. Kimi K2.6 has reached the top of the leaderboard for 3…

model-releaseskimi-moonshot--x

An open source model has returned to #1 on the 3D Design leaderboard by Design Arena. Kimi K2.6 has reached the top of the leaderboard for 3D Design, ahead of models 10X more expensive like Opus 4.7 b

Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking

arXiv:2605.23733v1 Announce Type: cross Abstract: Whole-body tracking (WBT) models have become a key foundation for humanoid robots, enabling them to imitate diverse motions with high fidelity. Traini

Anytime Training with Schedule-Free Spectral Optimization

arXiv:2605.23061v1 Announce Type: cross Abstract: Standard neural network training relies on learning-rate schedules tied to a fixed horizon, leading to strong path dependence and costly re-tuning as

Approaching I/O-optimality for Approximate Attention

arXiv:2605.23751v1 Announce Type: new Abstract: We revisit the I/O complexity of attention in large language models. Given query-key-value matrices Q,K,VinR^{nimes d}, and a machine with fast memory s

AraHopeCorpus: Annotation Guidelines and Dataset for Hope Speech in Arabic Social Media Crisis Discourse

arXiv:2605.23325v1 Announce Type: new Abstract: Social media has become a crucial arena for shaping public narratives during armed conflicts, providing space for both harmful and constructive communic

Archimedean Copula Inference via Taylor-Mode AD

arXiv:2605.23134v1 Announce Type: new Abstract: No existing nested Archimedean copula tool handles all three of (a) arbitrary per-variable (right-)censoring in survival analysis, (b) arbitrary nesting

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

arXiv:2605.23243v1 Announce Type: cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM

As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs

arXiv:2605.23147v1 Announce Type: cross Abstract: Role prompts of the form As X, do Y admit a clean linear decomposition at one specific site in the residual stream: the prompt-to-answer transition --

Asking For An Old Friend: Diagnosing and Mitigating Temporal Failure Modes in LLM-based Statutory Question Answering

arXiv:2605.23497v1 Announce Type: new Abstract: Large language models are increasingly used for legal research, yet their fixed training cutoffs and reliance on static parametric knowledge are at odds

Atom-level Protein Representation Learning Improves Protein Structure Prediction

arXiv:2605.22133v2 Announce Type: replace-cross Abstract: Recent advances in generative modeling show that pretrained representations can improve generation as conditioning features or alignment targe

Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics

arXiv:2510.12787v4 Announce Type: replace Abstract: We present Ax-Prover, a multi-agent system for automated theorem proving in Lean that can solve problems across diverse scientific domains and opera

Benchmarking and Enhancing VLM for Compressed Image Understanding

arXiv:2512.20901v2 Announce Type: replace Abstract: With the rapid development of Vision-Language Models (VLMs) and the growing demand for their applications, efficient compression of the image inputs

Benchmarking Google Embeddings 2 against Open-Source Models for Multilingual Dense Retrieval and RAG Systems

arXiv:2605.23618v1 Announce Type: new Abstract: We benchmark Google Embeddings (GE2), a Vertex-AI-hosted bi-encoder with 2,048-token context and explicit task-type conditioning, against five open-sour

BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems

arXiv:2605.22866v1 Announce Type: new Abstract: Compound AI systems route tasks through hierarchies of specialised components. Attribution is dominated by Shapley-based methods (SHAP), which decompose

Brain-LLM Alignment Tracks Training Data, Not Typology

arXiv:2605.23032v1 Announce Type: cross Abstract: Brain-LLM alignment is well established in English, yet the brain's language network is neuroanatomically universal across languages. Does alignment a

BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models

arXiv:2602.18788v3 Announce Type: replace Abstract: We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP

Can AI Guess What You Know? Performance Comparison of Large Language Models for Human Domain Knowledge Estimation From Communication Logs

arXiv:2605.22971v1 Announce Type: new Abstract: Employees often struggle to identify ``who knows what,'' leading to organizational productivity losses. We investigate whether Large Language Models (LL

Canadians be like come to our Toronto tech week party

Toronto Tech Week is an annual event in Toronto, Canada that brings together technology professionals, entrepreneurs, and innovators for networking, learning, and celebration of the local tech ecosyst

model-releasescohere--x

CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels

arXiv:2605.23254v1 Announce Type: new Abstract: Learning from real-world data is frequently hindered by the compound challenge of long-tailed class distributions and noisy annotations. Existing method

CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering

arXiv:2605.23216v1 Announce Type: new Abstract: Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception t

ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models

arXiv:2605.23694v1 Announce Type: new Abstract: Chart descriptions are essential for accessibility, cross-modal retrieval, and assisting readers in extracting insights from complex visualizations. As

CHRONOS: Temporally-Aware Multi-Agent Coordination for Evolving Data Marketplaces

arXiv:2605.23887v1 Announce Type: cross Abstract: Temporal knowledge-graph data marketplaces face three coupled failures in static designs: stale hybrid index shortcuts reduce recall as edges evolve,

ComfyUI-Angelo now supports Qwen Edit

model-releasesr-stablediffusion

ComfyUI-Angelo now supports Qwen-Image-Edit, an advanced image editing model that provides text editing features and the ability to edit both semantics and appearance of images. The model applies Qwen

Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models

arXiv:2605.23893v1 Announce Type: new Abstract: We propose Complete-muE, a framework which targets hyperparameter transfer across dense FFN and any Mixture-of-Experts (MoE) setups in transformer block

Computable Fairness: Boltzmann-Softmax Control for AI Resource Allocation

arXiv:2605.22827v1 Announce Type: cross Abstract: In large-scale AI systems, allocating scarce resources such as GPU compute time and bandwidth among multiple agents is a critical challenge. Conventio

Convex Optimization for Alignment and Preference Learning on a Single GPU

arXiv:2605.23244v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) to align with human preferences has driven the success of systems such as Gemini and ChatGPT. However, approach

Cost-Effective Model Evaluation with Meta-Learning

arXiv:2605.23595v1 Announce Type: cross Abstract: The rapid growth of machine learning has produced an ever-expanding ecosystem of models, making it increasingly challenging to verify the reliability

Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization

arXiv:2605.23391v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) for coupled multiphysics systems suffer systematic accuracy degradation as inter-equation coupling strengthens.

CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models

arXiv:2605.23699v1 Announce Type: new Abstract: Video prediction is increasingly viewed as a path toward generalizable world models, yet it remains unclear whether these systems learn underlying causa

Cultural Adaptation in Large Language Models for Political Discourse

arXiv:2605.23332v1 Announce Type: new Abstract: The integration of large language models into political discourse analysis creates new opportunities for comparative research, policy analysis, and civi

CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception

arXiv:2605.23655v1 Announce Type: cross Abstract: High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising s

D2 Actor Critic: Diffusion Actor Meets Distributional Critic

arXiv:2510.03508v3 Announce Type: replace Abstract: We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expressive diffusion policies online effectively. At its

DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architectures

arXiv:2511.15503v2 Announce Type: replace-cross Abstract: High-performance Host processors can integrate Processing-In-Memory (PIM) devices, which can accelerate memory-intensive kernels of Machine Le

DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs

arXiv:2605.23629v1 Announce Type: new Abstract: Medical diagnosis is not a single prediction from a fully specified vignette. It is a sequential workup: clinicians decide what evidence to obtain, revi

Decomposing and Measuring Evaluation Awareness

arXiv:2605.23055v1 Announce Type: cross Abstract: Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet t

Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval

arXiv:2605.23826v1 Announce Type: cross Abstract: Keyframe selection is a direct way to provide verifiable visual evidence for long-video question answering (QA). Queries differ in what they require,

Decomposition-Based Modular Conformal Prediction for Two-Stage Modeling

arXiv:2510.04406v2 Announce Type: replace-cross Abstract: Conformal prediction offers finite-sample coverage guarantees under minimal assumptions. However, existing methods treat the entire modeling p

Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization

arXiv:2605.23355v1 Announce Type: new Abstract: Temporal Action Localization (TAL) has been extensively studied in generic video understanding, while fine-grained sports scenarios, such as professiona

DeepSeek V4 Flash IS BACK on Nous Portal for FREE for use in Hermes Agent! Check it out at https://portal.nousresearch.com/manage-subscripti…

model-releasesnous-research--x

DeepSeek V4 Flash model has been made available again on the Nous Research portal at no cost for use with Hermes Agent applications. Users can access and utilize this model through the Nous portal's s

DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selection

arXiv:2605.23281v1 Announce Type: new Abstract: Monocular metric depth estimation has achieved strong progress with large-scale training and universal-camera modeling, yet robust deployment across div

Design and Report Benchmarks for Knowledge Work

arXiv:2605.23262v1 Announce Type: new Abstract: The development of LLM agents has led to a growing body of work on knowledge-work AI, including coding, research, and healthcare. However, current knowl