Search: “model-releases”

eMEM: A Hybrid Spatio-Temporal Memory System For Embodied Agents

model-releasesarxiv-cs-ro

arXiv:2606.03374v1 Announce Type: new Abstract: We present eMEM (Embodied Memory), a hybrid graph-based memory system for embodied agents operating in physical environments. Current agent memory archi

Model Releases

Enginuity: A Dataset and Benchmark for Vision-Language Understanding of Engineering Diagrams

DGX agent

arXiv:2606.03410v1 Announce Type: new Abstract: Engineering diagrams pose a distinct challenge for vision-language models: unlike natural images or general documents, they encode information through d

model-releasesarxiv-cs-cv

3 Jun 2026

EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge

arXiv:2606.03363v1 Announce Type: new Abstract: Text-to-SQL enables natural language access to databases, and recent LLMs have substantially advanced its capabilities. Existing benchmarks such as Spid

ERP-XTTN: Interpretable Prototype-Guided Cross-Attention for Cross-Subject ERP Classification

arXiv:2606.02939v1 Announce Type: new Abstract: Interpretable brain-computer interface classifiers that generalize across subjects without calibration remain an open challenge. We test whether prototy

EURO-5K: When Does Domain Pretraining Matter? Benchmarking Transformers for EU Reporting Obligation Extraction

arXiv:2606.02971v1 Announce Type: new Abstract: Extracting reporting obligations from EU legislation is critical for assessing and reducing regulatory reporting burden. However, distinguishing reporti

Evaluating and Calibrating LLM Confidence on Questions with Multiple Correct Answers

arXiv:2602.07842v2 Announce Type: replace Abstract: Confidence calibration is essential for making large language models (LLMs) reliable, yet existing training-free methods have been primarily studied

Evaluating LLMs' Effectiveness on Real-World Consumer Device Repair Questions

arXiv:2606.03331v1 Announce Type: cross Abstract: Consumer device repair is an important but underexplored testbed for large language models (LLMs). Repair tasks require reasoning over incomplete prob

EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents

arXiv:2606.03678v1 Announce Type: new Abstract: Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversa

Expanding Comfy With Claude Code https://x.com/i/broadcasts/1nJOLLXbrPWxR

This X broadcast from ComfyUI likely discusses updates or new features for integrating Claude AI code capabilities with ComfyUI, a node-based UI for AI image generation and processing workflows. The s

model-releasescomfyui--x

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning

arXiv:2606.03113v1 Announce Type: new Abstract: Large Language Models suffer from slow autoregressive inference. While self-speculative decoding accelerates this process, its efficiency is hampered by

FinStressTS: A Parametric Synthetic Benchmark for Time-Series Forecasting in Finance

arXiv:2606.03184v1 Announce Type: cross Abstract: Financial forecasting is difficult due to low signal-to-noise ratios, latent factors, heavy tails, regime shifts, and jumps. Real-world benchmarks off

Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling

arXiv:2606.02837v1 Announce Type: cross Abstract: Accurate translation from Natural Language to First-Order Logic (NL-to-FOL) underpins neurosymbolic AI systems and Natural Language Inference (NLI), m

FlashMLA-ETAP: Efficient Transpose Attention Pipeline for Accelerating MLA Inference on NVIDIA H20 GPUs

arXiv:2506.01969v3 Announce Type: replace-cross Abstract: Efficient inference of Multi-Head Latent Attention (MLA) is challenged by deploying the DeepSeek-R1 671B model on a single Multi-GPU server. T

Forecasting Conceptual Diffusion in Science: The Case of Quantum Computing

arXiv:2606.03919v1 Announce Type: cross Abstract: Understanding and anticipating scientific change requires models that distinguish between endogenous consolidation and exogenous diffusion of scientif

From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models

arXiv:2606.03660v1 Announce Type: new Abstract: Large language models are increasingly used as chemistry assistants, yet most chemistry benchmarks still score only final answers. This masks a critical

From Local Training to Large-Scale Mapping: A Comparative Assessment of Machine Learning and Deep Learning for Transferable Satellite-Derived Bathymetry

model-releasesarxiv-cs-cv

arXiv:2606.02764v1 Announce Type: new Abstract: Satellite-derived bathymetry (SDB) from multispectral imagery is cost-effective but scales poorly across regions, especially in optically complex coasta

From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting

arXiv:2606.03097v1 Announce Type: new Abstract: Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover

From Prompt to Service: An SLM-Based Agent Orchestration Gateway for AI-Driven Virtual Worlds

arXiv:2606.03557v1 Announce Type: new Abstract: As generative AI capabilities expand, AI-driven virtual worlds face a growing architectural challenge. Users interact through in-world interfaces in mul

From Script to Semantics: Prompting Strategies for African NLI

arXiv:2606.03304v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated in multilingual settings, yet their inference behavior in low-resource African languages remains

Frontier models are powerful advisors. On @harvey's Legal Agent Benchmark, a GLM 5.1 worker using Claude Opus 4.7 as a sparse advisor reache…

model-releasesfireworks-ai--x

Frontier models are powerful advisors. On @harvey's Legal Agent Benchmark, a GLM 5.1 worker using Claude Opus 4.7 as a sparse advisor reached 18/100 all-pass versus 14/100 for Opus alone, at 39% of th

Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models

arXiv:2606.03165v1 Announce Type: cross Abstract: The language used by digital chat assistants such as ChatGPT can diverge from human expectations (misalignment). Research, mostly on Scientific Englis

G^2C-MT: Graph-Guided Context Selection for Document-Level Machine Translation

arXiv:2606.03078v1 Announce Type: new Abstract: Effective document-level machine translation (DocMT) requires capturing long-range discourse dependencies. Recent work has explored retrieval-based and

Gate AI: LLM Security Benchmark Evaluation Methodology and Results

arXiv:2606.02959v1 Announce Type: new Abstract: Published evaluations of prompt-injection and jailbreak detectors for Large Language Models often suffer from two systematic weaknesses: per-dataset thr

Gemma 4 12B is here! Dense, mid-sized Gemma that fits right on your laptop - released by @google under Apache 2.0 Available now in LM Studio…

model-releaseslm-studio--x

Gemma 4 12B is a newly released dense language model from Google available under the Apache 2.0 open license, designed for mid-sized computing resources that can run locally on personal computers. The

Gemma 4 model load issues fixed in engine version 2.20.1. lms runtime update --all

model-releaseslm-studio--x

Gemma 4 model load issues fixed in engine version 2.20.1. lms runtime update --all Gemma 4 12B is here! Dense, mid-sized Gemma that fits right on your laptop - released by @google under Apache 2.0 Ava

Gender-Dependent Diagnostic Substitution in LLM Medical Triage: Same Symptoms, Unequal Urgency

arXiv:2606.03641v1 Announce Type: new Abstract: We investigate whether large language models produce different medical triage recommendations for identical neurological symptoms when only the patient'

Generating Rectifiable Measures through Neural Networks

arXiv:2412.05109v2 Announce Type: replace Abstract: We derive universal approximation results for the class of (countably) m-rectifiable measures. Specifically, we prove that m-rectifiable measures ca

Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations

arXiv:2510.21011v3 Announce Type: replace-cross Abstract: As generative AI tools are increasingly used to portray people in professional roles, understanding their racial and gender representational b

GeoDrive-Bench: Benchmarking Region-Specific Multimodal Reasoning in Autonomous Driving

model-releasesarxiv-cs-cv

arXiv:2606.02774v1 Announce Type: new Abstract: Vision-language models (VLMs) for autonomous driving have shown promising performance, but their ability to handle region-specific traffic rules remains

Geometry-Aware Tabular Diffusion

arXiv:2606.02607v1 Announce Type: cross Abstract: Tabular synthesis is critical for privacy-preserving sharing and augmentation, yet diffusion models rely on implicit mechanisms to capture inter-colum

Giving a talk this Sunday June 7th at @agihouse_org talking about DeepSeek V4 on @togethercompute! Come hang and let's talk inference!

model-releasestogether-ai--x

A Together AI representative announced a talk scheduled for Sunday, June 7th at AGI House focusing on DeepSeek V4 and inference optimization on Together Compute's platform. The event was promoted as a

GN0: Toward a Unified Paradigm for Generation, Evaluation, and Policy Learning in Visual-Language Navigation

model-releasesarxiv-cs-ro

arXiv:2606.03682v1 Announce Type: new Abstract: Embodied navigation connects intelligent agents with the physical world and is fundamental for general robotic intelligence. Limited availability and qu

Google introduces Gemma 4 12B, a unified, encoder-free open multimodal model that can run locally on devices with 16GB of VRAM or unified memory (Carl Franzen/VentureBeat)

Carl Franzen / VentureBeat: Google introduces Gemma 4 12B, a unified, encoder-free open multimodal model that can run locally on devices with 16GB of VRAM or unified memory — While many AI open source

model-releasestechmeme

Google launches Dreambeans, an AI app that curates daily stories from Google data

model-releasessiliconangle

Google LLC today launched Dreambeans, an experimental app from its Google Labs division that uses artificial intelligence to assemble a finite set of personalized daily stories drawn from a user’s own

.@GoogleDeepMind's Gemma 4 - 12B is available on Ollama! Chat: ollama run gemma4:12b-mlx Hermes Agent: ollama launch hermes --model gemma4:1…

.@GoogleDeepMind's Gemma 4 - 12B is available on Ollama! Chat: ollama run gemma4:12b-mlx Hermes Agent: ollama launch hermes --model gemma4:12b-mlx Claude Code: ollama launch claude --model gemma4:12b-

model-releasesollama--x

Google's new Gemma 4 12B model is designed to run on any laptop with 16GB of RAM

model-releasesars-technica

Google DeepMind released Gemma 4 12B, an open AI model that brings multimodal capabilities to everyday laptops by processing text, images, and audio natively without separate encoders. Small enough to

GPU-Parallel Multi-Task Reinforcement Learning with Demonstration Guided Policy Optimization

model-releasesarxiv-cs-ro

arXiv:2606.03335v1 Announce Type: new Abstract: Large scale GPU-parallel reinforcement learning has changed what can be trained in robot simulation, yet most systems still optimize one specialist poli

Greener Than Humans? Environmental Attitudes in Large Language Models

arXiv:2606.02741v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in sustainability-related decision support, reporting, and public communication, yet little systemati

GTBench: A Curriculum-Grounded Benchmark for Evaluating LLMs as Mathematical Research Assistants in Graph Theory

arXiv:2606.03144v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as self-study assistants in technical disciplines, yet their reliability as mathematical reasoning as

Had Claude Code build a snake game where the snake becomes aware it is in the game and then... stuff happens. Some impressive creative decis…

model-releasesethan-mollick--x

Had Claude Code build a snake game where the snake becomes aware it is in the game and then... stuff happens. Some impressive creative decisions by the AI (& also some very AI ones), I just gave a fir

Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs

arXiv:2606.02628v1 Announce Type: cross Abstract: We investigate whether open-source LLMs encode a linearly separable truthfulness signal in their hidden states, and at which network depth this signal

Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization

arXiv:2606.03022v1 Announce Type: cross Abstract: Hallucination in Large Language Models (LLMs), characterized by the generation of content inconsistent with contextual facts or logical constraints --

Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning

arXiv:2606.03918v1 Announce Type: new Abstract: AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets. The har

Honesty in Causal Forests: When It Helps and When It Hurts

arXiv:2506.13107v4 Announce Type: replace Abstract: Causal forests estimate how treatment effects vary across individuals, guiding personalized interventions in areas like marketing, operations, and p

how does the brain build and track an internal state of the world from (possibly incomplete and noisy) visual observations? i believe visual…

model-releasesyann-lecun--x

how does the brain build and track an internal state of the world from (possibly incomplete and noisy) visual observations? i believe visual state tracking will be the grand challenge for vision in th

How Many Trees in a Random Forest? A Revisited Approach with Plateau Search and Optuna Integration

arXiv:2606.03549v1 Announce Type: new Abstract: Hyperparameter optimization (HPO) for Random Forest faces a specific difficulty in tuning the number of trees: the predictive score typically improves m

How Quantization Changes Interpretable Features: A Sparse Autoencoder Analysis of Language Models

arXiv:2606.03002v1 Announce Type: cross Abstract: Quantization is a standard path to deploying large language models, and a quantized model is typically judged acceptable when its perplexity or downst

How Wasmer used Codex to build a Node.js runtime for the edge

Wasmer leveraged OpenAI's Codex to develop a Node.js runtime optimized for edge computing environments. The project demonstrates how AI-assisted code generation can accelerate the creation of speciali

model-releasesopenai