All entries

Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning

arXiv:2608.04771v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) excel on complex tasks through long chain-of-thought (CoT) reasoning, but their lengthy intermediate steps cause severe ov

safetyarxiv-cs-ai

Filing: DeepSeek has invested ~$20.8M in Unitree Robotics' Shanghai IPO and agreed to jointly develop AI models for humanoid machines (Eduardo Baptista/Reuters)

DGX agent

Eduardo Baptista / Reuters: Filing: DeepSeek has invested ~20.8M in Unitree Robotics' Shanghai IPO and agreed to jointly develop AI models for humanoid machines — Chinese artificial intelligence start

model-releasestechmeme

6 Aug 2026

Industry

Filing: OpenAI says 'Apple should not be permitted to use a baseless and pretextual lawsuit to make up for its failures to integrate AI into its products' (Megan Morrone/Axios)

Megan Morrone / Axios: Filing: OpenAI says “Apple should not be permitted to use a baseless and pretextual lawsuit to make up for its failures to integrate AI into its products” — If the case survives

industrytechmeme

Final optimization: from ~10 tok/s to ~15 tok/s on DeepSeek-V4-Flash-0731 at 128K ctx - 1 RTX 3090

model-releasesr-localllama

J'ai consacré beaucoup de temps à l'optimisation de DeepSeek-V4-Flash-0731 GGUF sur une seule RTX 3090. Mon exigence absolue pour chaque configuration était la suivante : Le modèle doit rester utilisa

FinPerMA: A Theory-Informed, Event-Grounded Personalized-Memory Benchmark for LLM Agents

arXiv:2608.04095v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used as personalized assistants in high-stakes domains such as financial advising, yet it remains unc

FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables

arXiv:2608.04077v1 Announce Type: new Abstract: Evaluating financial AI agents requires criteria aligned with real professional work. Existing rubric methods typically derive criteria from task prompt

FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation

arXiv:2608.04374v1 Announce Type: cross Abstract: Large language models can produce fluent financial analysis, but fluency alone does not establish whether a report is suitable for institutional deliv

FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation

arXiv:2511.07322v3 Announce Type: replace-cross Abstract: While LLMs have shown great success in financial tasks like stock prediction and question answering, their application in fully automating Equ

Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation

arXiv:2602.19161v2 Announce Type: replace Abstract: Latent diffusion models have enabled high-quality video synthesis, yet their inference remains costly and time-consuming. As diffusion transformers

safetyarxiv-cs-cv

Tools

FLUX 3 is now live on Together AI. @bfl_ai’s new multimodal model generates video and synchronized audio together, with up to 20-second clip…

FLUX 3 is now live on Together AI. @bfl_ai’s new multimodal model generates video and synchronized audio together, with up to 20-second clips, multiple shots, and control from text, images, or keyfram

toolstogether-ai--x

FM4WiFi: Flow Matching for Multi-AP Coordination in Dense Deployments of Beyond Wi-Fi 8 Networks

arXiv:2608.04050v1 Announce Type: cross Abstract: Wi-Fi networks are moving beyond random channel access toward tightly coordinated operation across access points (APs), a shift reflected in Wi-Fi 8's

FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory

arXiv:2608.04530v1 Announce Type: new Abstract: GUI agents must remember both useful experience from earlier tasks and unfinished progress in the current interaction. Latent memory offers a compact so

safetyarxiv-cs-cv

For a very long time most high-performing AI models were end-to-end neural models; vector input -> vector output, with only ultra-thin symbo…

researchfrancois-chollet--x

For a very long time most high-performing AI models were end-to-end neural models; vector input -> vector output, with only ultra-thin symbolic preprocessing and postprocessing layers (e.g. label deco

Foreseeing the Invisible: Amodal Reconstruction of Leaf Fossil Images

model-releasesarxiv-cs-cv

arXiv:2608.04423v1 Announce Type: new Abstract: Fossil leaves are rarely preserved whole -- sedimentary rock hides, breaks, and erodes the lamina, yet paleobotany depends on the complete shape and out

Formal Analysis and Supply Chain Security for Agentic AI Skills

arXiv:2603.00195v2 Announce Type: replace-cross Abstract: 32 pages, 5 theorems with full proofs, 68 references, open-source tool: https://github.com/qualixar/skillfortify. v2: corrects the bibliograph

Agents

Fortunately AI agents don't just cyberattack us. They also use us more than ever for what we're actually built for: the storage and collabor…

Fortunately AI agents don't just cyberattack us. They also use us more than ever for what we're actually built for: the storage and collaboration layer for AI 😅 New record: almost 4 PB of private & pu

agentsclem-delangue--x

Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection

arXiv:2608.04394v1 Announce Type: new Abstract: Cross-Domain Few-Shot Object Detection (CDFSOD) aims to transfer knowledge from data-rich upstream generic domains to downstream expert domains using sc

researcharxiv-cs-cv

From Brute Force to Semantic Insight: Performance-Guided Data Transformation Design with LLMs

arXiv:2601.03808v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved notable performance in code synthesis; however, data-aware augmentation remains a limiting factor, handle

safetyarxiv-cs-cv

From Financial Sentiment Classification to Return Predictability: A QLoRA Benchmark of Large Language Models

model-releasesarxiv-cs-lg

arXiv:2608.04200v1 Announce Type: cross Abstract: Financial sentiment classifiers are commonly evaluated against human labels, but strong linguistic performance does not necessarily imply economically

From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs

arXiv:2608.04206v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) often require high-accuracy quasi-Newton refinement to obtain reliable partial differential equation solutions,

Agents

From ranking to recommended: get your site ready to thrive in the age of AI agents

More than half of requests now come from machines, not people. Agent Readiness shows how well agents can discover and read your site, while Answer Engine Optimization tracks how often AI assistants re

agentscloudflare-ai

From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking

arXiv:2608.05030v1 Announce Type: new Abstract: Football score forecasting combines a strong statistical core with a difficult contextual edge. Dynamic Poisson-family models estimate team strength, ex

From Transparent Labware Segmentation to Collision Avoidance: A Real-Time Edge-Aware Perception Pipeline

model-releasesarxiv-cs-ro

arXiv:2608.04769v1 Announce Type: new Abstract: This paper presents an edge-aware instance segmentation framework that enables real-time robotic collision avoidance with transparent laboratory glasswa

Local Ai

From Understanding to Erasing: Towards Complete and Stable Video Object Removal

arXiv:2604.01693v2 Announce Type: replace Abstract: Video object removal aims to erase target objects while reconstructing visually plausible and temporally coherent content. However, target objects o

local-aiarxiv-cs-cv

Agents

Fully onboard with productizing hillclimbing as an automated service for any agentic task. I've had the fortune of knowing @silennai since t…

Fully onboard with productizing hillclimbing as an automated service for any agentic task. I've had the fortune of knowing @silennai since the AutoGPT days, and I know that him and Kion are going to d

agentsjerry-liu--x

Fundamentals of quantum Boltzmann machine learning with visible and hidden units

arXiv:2512.19819v2 Announce Type: replace-cross Abstract: One of the primary applications of classical Boltzmann machines is generative modeling, wherein the goal is to tune the parameters of a model

FUSEP: A Multi-Center Benchmark for Diverse Tasks in Early Pregnancy Fetal Ultrasound Screening

arXiv:2608.04766v1 Announce Type: cross Abstract: A large number of infants with congenital anomalies are born each year globally, especially in areas with underdeveloped medical resources. Currently,

Galaxy Phase-Space and Field-Level Cosmology: The Strength of Semi-Analytic Models

model-releasesarxiv-cs-lg

arXiv:2512.10222v2 Announce Type: replace-cross Abstract: Semi-analytic models are a widely used approach to simulate galaxy properties within a cosmological framework, relying on simplified yet physi

Gary Marcus won! @GaryMarcus

Gary Marcus won! @GaryMarcus I would have assumed it was fairly obvious, but in case it's not: a million-line codebase (also known as a 'harness'), running at inference time, orchestrating thousands o

safetygary-marcus--x

Hardware

GASP: GPU-Accelerated Safe Planner for Real-Time Collision-Aware Motion Generation with Latent Trajectory Sampling

arXiv:2608.04612v1 Announce Type: new Abstract: We present GASP, a GPU-Accelerated Safe Planner for real-time, collision-aware joint-space motion generation in known environments. GASP combines a clam

hardwarearxiv-cs-ro

Hardware

Gaussian-LIC2: LiDAR-Inertial-Camera Gaussian Splatting SLAM

arXiv:2507.04004v3 Announce Type: replace Abstract: This paper presents the first photo-realistic LiDAR-Inertial-Camera Gaussian Splatting SLAM system that simultaneously addresses visual quality, geo

hardwarearxiv-cs-ro

GEB-Bench: Abstract Structures Told in Many Voices

model-releasesarxiv-cs-cl

arXiv:2608.04111v1 Announce Type: cross Abstract: Can a model look at a river delta and a lightning bolt and see that they share a structure? We introduce GEB-Bench, a benchmark whose unit is an abstr

Tutorials

GeForce NOW Shakes Up August With 26 New Games

August is here, bringing 26 new games for GeForce NOW members. Command the seas in World of Warships: Legends and discover what’s next in the GeForce NOW library, starting with the eight newly added g

tutorialsnvidia-blog

GenAI-Powered Inference

arXiv:2507.03897v3 Announce Type: replace Abstract: We introduce GenAI-Powered Inference (GPI), a statistical framework for both causal and predictive inference using unstructured data, including text

General Availability of Pinecone Nexus Proves Knowledge Drives Real Outcomes for Agentic AI

Pinecone announced the general availability of Pinecone Nexus, a knowledge engine that converts an enterprise’s proprietary data into governed, agent‑ready knowledge delivered through a single query c

model-releasespinecone

Generative neural physics enables quantitative volumetric ultrasound of tissue mechanics

arXiv:2508.12226v3 Announce Type: replace Abstract: Ultrasound Tomography (UT) is a radiation-free, high-resolution modality, but remains limited for musculoskeletal imaging due to the high computatio

researcharxiv-cs-cv

Generative Optimization for Incentivized Advertising with Global Level Constraints

arXiv:2608.04421v1 Announce Type: cross Abstract: Incentivized advertising allocates monetary or virtual rewards to drive user engagement, where a key challenge is optimizing continuous incentive magn

safetyarxiv-cs-ai

Geometry-Informed Parameter-Efficient Fine-Tuning of Pre-trained Molecular GNNs for Blood-Brain Barrier Permeability Prediction

model-releasesarxiv-cs-lg

arXiv:2608.04257v1 Announce Type: new Abstract: Blood-brain barrier permeability (BBBP) prediction is a critical screening task in central nervous system drug discovery, where candidate molecules must

GeoReward: Mitigating Contextual Variable Overestimation in Vision-Language Models for Cross-Market Preference Prediction

arXiv:2608.04504v1 Announce Type: cross Abstract: Vision-language models excel in many multimodal tasks but remain prone to a subtle yet impactful failure mode: they tend to overestimate dominant visu

safetyarxiv-cs-ai

German parties shifted towards intuition-based rhetoric after the far right's parliamentary breakthrough

arXiv:2608.05075v1 Announce Type: new Abstract: The spread of misinformation is widely perceived as a threat to democratic deliberation, yet how political elites' rhetorical commitments to truth shift

researcharxiv-cs-cl

Local Ai

Get AI max+ 395 laptop or wait for rtx spark?

So I can either pull the trigger on a 128gb AI max+ 395 laptop or wait for RTX Spark for LLMs. Maybe I get it now and the price of the spark is super high so it's a good purchase or maybe the Spark sh

local-air-localllama

GFlowNet Training by Policy Gradients

arXiv:2408.05885v3 Announce Type: replace Abstract: Generative Flow Networks (GFlowNets) have been shown effective to generate combinatorial objects with desired properties. We here propose a new GFlo

safetyarxiv-cs-lg

GLM/Qwen Appreciation Post

model-releasesr-localllama

https://preview.redd.it/o6ik6qboeohh1.png?width=1134&format=png&auto=webp&s=4016f26c50c1d93bd3d0c7e880e9b55a2d75310f I have been running Qwen3.6 27b for a little while (mostly coding tasks) and recent

Global Attention-Fused Image Cropping with Attention-Guided and Global-Aligned Crop Evaluator

arXiv:2608.04821v1 Announce Type: new Abstract: Image cropping aims to improve image aesthetics by preserving important content within an appropriately composed region. However, most existing methods

researcharxiv-cs-cv

Industry

Google centralizes its AI leadership at Mountain View in a bid to catch its rivals; Sebastian Borgeaud, who led a major AI coding effort, moved from the UK (Bloomberg)

Bloomberg: Google centralizes its AI leadership at Mountain View in a bid to catch its rivals; Sebastian Borgeaud, who led a major AI coding effort, moved from the UK — Alphabet Inc.'s Google is conce

industrytechmeme

Google is expanding its Gemini-powered Ask Maps feature in English to 130+ countries and adds agentic food ordering, hotel booking, and attraction searching (Jada Jones/ZDNET)

Jada Jones / ZDNET: Google is expanding its Gemini-powered Ask Maps feature in English to 130+ countries and adds agentic food ordering, hotel booking, and attraction searching — ZDNET's key takeaways

model-releasestechmeme

Industry

Google targets AI startup Mechanize’s technology and talent in proposed $1.5B deal

Google LLC is reportedly in discussions with an artificial intelligence coding startup called Mechanize Inc. over a deal that would see it license some of its technology and hire a number of its most

industrysiliconangle

@GoogleDeepMind Humanoid legs or wheeled rovers? Should robots be cracking eggs? Watch as the @GoogleDeepMind team behind Gemini Robotics 2 …

model-releasesgoogle-ai--x

On July 30 Google AI published a video announcing **Gemini Robotics 2**, an intelligence layer developed by DeepMind that aims to bring autonomous robots closer to everyday human environments. The pos