model releases

A comparative study of transformer-based embeddings for topic coherence

arXiv:2605.28832v1 Announce Type: cross Abstract: Topic modeling is a branch of Natural Language Processing (NLP) that aims to organize large collections of texts into coherent groups according to wor

Model Releases

A Computational Method for Solving the Stochastic Joint Replenishment Problem in High Dimensions

DGX agent

arXiv:2511.11830v2 Announce Type: replace-cross Abstract: We consider a discrete-time formulation for a class of high-dimensional stochastic joint replenishment problems. First, we approximate the pro

model-releasesarxiv-cs-lg

29 May 2026

A Dual-Path Architecture for Scaling Compute and Capacity in LLMs

arXiv:2605.30202v1 Announce Type: new Abstract: Looped transformers apply a shared block multiple times and have emerged as a parameter-efficient route to scaling compute in language models. However,

A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning

arXiv:2605.29454v1 Announce Type: new Abstract: While Membership Inference Attacks (MIAs) are the prevailing method for identifying training data, their application has expanded into privacy auditing

A Minimal Bifurcation Model of Load Imbalance in a Softmax Mixture-of-Experts Router

arXiv:2605.29121v1 Announce Type: cross Abstract: We propose a minimal dynamical model of adaptive softmax routing for a two-expert Mixture-of-Experts (MoE) layer. The model is obtained as a mean-fiel

A new completely parameter-free clustering algorithm for unsupervised classification of BATSE gamma-ray bursts

arXiv:2605.30175v1 Announce Type: cross Abstract: Cluster analysis is a widely applied machine learning technique to understand the existing patterns in the population of gamma-ray bursts (GRBs), in o

A Novel Tensor Product-Based Neural Network for Solving Partial Differential Equations

arXiv:2605.29688v1 Announce Type: new Abstract: This paper presents the Tensor Product Network (TPNet), a novel neural architecture for efficient and accurate function approximation and PDE solving. T

A Progress-Aware Leader-Follower Midair Docking System for Dual-Drone Aerial Manipulation

model-releasesarxiv-cs-ro

arXiv:2605.29410v1 Announce Type: new Abstract: Reliable midair docking between small unmanned aerial vehicles (UAVs) is essential for modular aerial cooperation and manipulation, but it requires prec

A Training-Time Diagnostic for Generalization via the Log-Alignment Ratio

arXiv:2605.28975v1 Announce Type: new Abstract: We study the log-alignment ratio (LAR), a measure of parameter-activation alignment, introduced in parameterization theory. We reformulate it as the ove

A Triple-Modal Contrastive Learning Framework with Sequence, Graph, and 3D Features for Drug-Target Interaction Prediction

arXiv:2605.29926v1 Announce Type: new Abstract: Accurate prediction of drug-target interactions (DTI) is critical for drug discovery. Existing methods often rely on single-modal representations (e.g.,

Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging

arXiv:2605.29489v1 Announce Type: new Abstract: Weight-space model merging is usually formulated as an algebraic operation on checkpoints, yet at LLM scale the limiting resource is often the set of ex

Active Learning for Machine Learning Driven Molecular Dynamics

arXiv:2509.17208v3 Announce Type: replace Abstract: Machine-learned coarse-grained (CG) potentials are fast, but degrade over time when simulations reach under-sampled bio-molecular conformations, and

Adapting Automotive Aerodynamics Surrogates to New Vehicle Families via Transfer Learning

arXiv:2605.27968v1 Announce Type: cross Abstract: Deploying Scientific Machine Learning surrogates in industrial CFD workflows requires adapting pretrained models to new vehicle families without large

Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation

arXiv:2605.29992v1 Announce Type: new Abstract: Sentence embeddings are a foundational component for semantic search, clustering, classification, and retrieval-augmented generation. This paper present

AfriScience-MT: Towards Decolonizing Science in Africa through Text Translation

arXiv:2605.29741v1 Announce Type: new Abstract: The dominance of colonial languages in African education and scientific communication limits how hundreds of millions of speakers of African languages a

AgentCVR: Active Multi-Agent Cross-Video Reasoning via Script-Simulated Reinforcement Learning

arXiv:2605.29643v1 Announce Type: new Abstract: Cross-Video Reasoning (CVR) has emerged as a critical frontier in multimodal intelligence, requiring models to retrieve, align, and aggregate evidence d

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

arXiv:2605.29801v1 Announce Type: new Abstract: Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhi

AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning

arXiv:2602.23258v2 Announce Type: replace Abstract: While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information from individual agents. C

AI can give researchers the freedom to pursue “crazier” ideas. For Terence Tao, AI creates more room to experiment, test unexpected paths, a…

AI tools are enabling researchers, including renowned mathematician Terence Tao, to explore unconventional and high-risk ideas by handling routine computational tasks and verification work. This techn

model-releasesopenai--x

AI startup Shift launches a free home cleaning service in NYC to record first-person video with a camera-equipped cap and use it to train robots (Robert Hart/The Verge)

Robert Hart / The Verge: AI startup Shift launches a free home cleaning service in NYC to record first-person video with a camera-equipped cap and use it to train robots — Shift says a ‘magic hat’ wi

model-releasestechmeme

Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization

arXiv:2605.29396v1 Announce Type: new Abstract: Safety alignment for large language models (LLMs) aims to reduce harmful or unsafe behavior while preserving general utility. However, recent findings r

Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models

arXiv:2605.30038v1 Announce Type: cross Abstract: Diffusion models generate highly realistic images but often struggle with precise text-image alignment. While recent post-training methods improve ali

AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation

arXiv:2512.01334v2 Announce Type: replace Abstract: Text-guided image-to-video generation has made substantial progress, yet it still struggles to execute text-specified edits that require substantial

AlloyDB Hot Standby: Faster failovers, consistent performance

model-releasesgoogle-cloud-ai

AlloyDB for PostgreSQL is a fully managed, PostgreSQL-compatible database service designed for the most demanding enterprise workloads. It combines the best of PostgreSQL with the power of Google, del

AMDP: Asynchronous Multi-Directional Pipeline Parallelism for Large-Scale Models Training

arXiv:2605.29664v1 Announce Type: cross Abstract: Pipeline parallelism is essential for large-scale model training, but existing asynchronous approaches often degrade convergence due to parameter mism

An End-to-End PyTorch Interface for Differentiable PDE Solvers: A RANS Model-Correction Study

arXiv:2605.28858v1 Announce Type: cross Abstract: This work presents an end-to-end strategy for solving inverse problems constrained by Partial Differential Equations within a fully differentiable Mac

Another proof point for the open-weights thesis. From @RampLabs: 'If we built this again, we'd lean more on open-weight models.' Ramp pointe…

model-releasesfireworks-ai--x

Another proof point for the open-weights thesis. From @RampLabs: 'If we built this again, we'd lean more on open-weight models.' Ramp pointed 10K agents at their own backend. Kimi K2.6 and DeepSeek V4

Anthropic's run-rate revenue hits $47 billion

model-releasessimon-willison

The most interesting thing about Anthropic's 65B Series H announcement is this line (emphasis mine): Since our Series G in February, adoption has continued to grow across global enterprise customers,

Apertus LLM Family Expansion via Distillation and Quantization

arXiv:2605.29128v1 Announce Type: new Abstract: The wide adoption of LLMs has led to their use in great variety of applications and scenarios, such as chatbot assistants and data annotation, creating

Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A PiSAR Benchmark

arXiv:2605.29400v1 Announce Type: new Abstract: We benchmark three supervised fine-tuned models against frontier zero-shot baselines on a 661-row held-out slice of PiSAR (Persona, intent, Screen, Acti

Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humans

arXiv:2410.10398v3 Announce Type: replace-cross Abstract: As large language models (LLMs) increasingly engage in complex social interactions, ensuring that their behaviors align with human ethical pri

AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Crystalline Materials

arXiv:2510.04704v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promising potential in scientific research, enabling tasks ranging from knowledge retrieval to propert

AttuneBench: A Conversation-Based Benchmark for LLM Emotional Intelligence

arXiv:2605.21739v2 Announce Type: replace Abstract: Emotional intelligence (EI), the ability to perceive, understand, and respond appropriately to others' emotional states, is central to human communi

Audio Deepfake Detection with Half-Truth Localisation Using Cross-Attentive Feature Fusion

arXiv:2605.29531v1 Announce Type: cross Abstract: Audio deepfake detection is well-studied as a binary problem, but partially manipulated speech, where a short synthesised segment is spliced into an o

Auditing Training-Free 3D Shape Retrieval with Diffused Geodesic Moments

arXiv:2605.29004v1 Announce Type: new Abstract: Reported retrieval scores for training-free shape descriptors conflate local signal design, normalization, aggregation, codebook fitting, and metric cho

AutoSizer: Automatic Sizing of Analog and Mixed-Signal Circuits via Large Language Model (LLM) Agents

arXiv:2602.02849v2 Announce Type: replace Abstract: The design of Analog and Mixed-Signal (AMS) integrated circuits remains heavily reliant on expert knowledge, with transistor sizing a major bottlene

Balancing Multimodal Learning through Label Space Reshaping

arXiv:2605.28869v1 Announce Type: cross Abstract: Multimodal learning often suffers from modality imbalance, where modalities that converge faster dominate optimization while others remain undertraine

Bandit Algorithms for Deep Brain Stimulation

arXiv:2601.12699v2 Announce Type: replace Abstract: Deep Brain Stimulation (DBS) is an effective treatment for Parkinson's disease, but conventional fixed-parameter stimulation can reduce battery life

Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation

arXiv:2605.29560v1 Announce Type: new Abstract: Parameterizing high-fidelity 'digital twins' of batteries is a critical yet challenging inverse problem that hinders the pace of battery innovation. Pre

'Be My Cheese?': Cultural Nuance Benchmarking for Machine Translation in Multilingual LLMs

arXiv:2602.04729v2 Announce Type: replace Abstract: We present a large-scale human evaluation benchmark for assessing cultural localisation in machine translation produced by state-of-the-art multilin

Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset

arXiv:2605.29462v1 Announce Type: cross Abstract: The emergence of Large Vision-Language Models (LVLMs) has substantially expanded model capabilities beyond text-only understanding, enabling unified i

Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting

arXiv:2509.23571v3 Announce Type: replace-cross Abstract: As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect a

Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation

arXiv:2605.28830v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly deployed in safety-critical applications, robust content moderation becomes essential. We present a c

Benchmarking Positional Encoding Strategies for Transformer-Based EEG Foundation Models

arXiv:2605.29754v1 Announce Type: new Abstract: Electroencephalography (EEG) is a widely used non-invasive technique for measuring brain activity in brain-computer interface (BCI) applications. Superv

Benchmarking Single-Factor Physical Video-to-Audio Generation

arXiv:2605.30339v1 Announce Type: new Abstract: Generative video-to-audio (V2A) models produce highly plausible soundtracks, but it remains unclear whether they capture the underlying physical process

BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents

arXiv:2605.29225v1 Announce Type: new Abstract: Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, lea

Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM Safety Evaluation in Chinese

arXiv:2605.29667v1 Announce Type: new Abstract: When Large Language Models (LLMs) are deployed in Chinese-language settings, a troubling pattern emerges: safety systems that work well in English break

Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization

arXiv:2605.28969v1 Announce Type: cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user. We introduce representational accuracy to measure how f