Search: “models”

arXiv:2507.07445v3 Announce Type: replace Abstract: Autonomous agents navigating human society must master both production activities and social interactions, yet existing benchmarks rarely evaluate t

arXiv:2606.28480v1 Announce Type: cross Abstract: As large language models and harness frameworks continue to advance, agents operating in terminals are increasingly capable of performing a broader ra

arXiv:2606.29964v1 Announce Type: new Abstract: Score distillation turns a pretrained 2D diffusion model into a 3D generator, but the per-step gradient is estimated from a single randomly chosen view:

What an honor to emcee the first day of @aiDotEngineer and introduce the Software Factories Track Thank you @swyx & team, and @KeycardLabs for the support. “A year ago @GeoffreyHuntley released the Ra

What's new in Claude Sonnet 5 Claude Sonnet 5 came out this morning. I always head straight for the 'what's new' developer docs because they tend to have more actionable information than the official

arXiv:2606.28376v1 Announce Type: cross Abstract: Long-horizon large language model (LLM) agents accumulate interaction trajectories that quickly exceed any practical prompt budget, and existing memor

arXiv:2606.29248v1 Announce Type: new Abstract: Vegetable prices in Sri Lanka are highly volatile because the market is largely import-isolated, so supply disruptions quickly drive prices up. This stu

arXiv:2606.30587v1 Announce Type: cross Abstract: Researchers and practitioners increasingly apply Large Language Models (LLMs) for automated vulnerability detection. Recent work has shown that LLMs a

arXiv:2412.15529v4 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) synergizes the retrieval of pertinent data with the generative capabilities of Large Language Models (LLM

arXiv:2606.27897v1 Announce Type: new Abstract: We present a design rationale, embedding model, and interactive visual-analysis system for exploring large wristwatch collections through heterogeneous

arXiv:2606.28044v1 Announce Type: new Abstract: In recent times, Large Language Models (LLMs) are increasingly being used for legal case judgement summarization. Most prior works have tried traditiona

This post discusses requested or required features for the next version of GLM (likely referring to Zhipu AI's large language model). The content appears to be a community discussion or announcement o

arXiv:2606.27962v1 Announce Type: new Abstract: This paper presents a cloud-native simulation infrastructure framework for embodied intelligence that supports large-scale training, standardized evalua

arXiv:2602.16065v2 Announce Type: replace-cross Abstract: As artificial intelligence (AI)-generated content proliferates, models are increasingly trained on their own outputs, risking progressive degr

arXiv:2606.27683v1 Announce Type: cross Abstract: Edge devices increasingly invoke large language models (LLMs) through API services for context aware edge intelligence, while edge generated data may

Chess engines tell you the best move. But grandmasters are human, they don’t always play it. So I built 'Kibitz': a human move predictor for chess broadcasts. I trained this model on my Nvidia RTX 508

DiScoFormer is a unified transformer architecture designed to handle both density estimation and score-based modeling across different probability distributions. The model enables a single framework t

arXiv:2504.16116v4 Announce Type: replace-cross Abstract: The Web3 ecosystem, underpinned by cryptographic primitives and decentralized consensus, represents a high-stakes environment where software v

arXiv:2606.27622v1 Announce Type: new Abstract: Byzantine-robust federated learning seeks to protect distributed model training from malicious or corrupted clients without requiring access to their pr

arXiv:2509.19376v2 Announce Type: replace-cross Abstract: We present a lightweight, model-agnostic temporal layer for RAG and use cybersecurity data to separate two problems that are usually conflated

arXiv:2606.28249v1 Announce Type: cross Abstract: Recently, Large Language Model (LLM)-based Text-to-Speech (TTS) models have achieved remarkable naturalness. However, the standard Supervised Fine-Tun

ComfyUI announced June product launches featuring desktop application improvements, MCP (Model Context Protocol) enhancements, and core engine upgrades during a live demonstration with audience Q&A se

arXiv:2606.28144v1 Announce Type: new Abstract: Reconstructing high-fidelity, relightable 3D avatars from a single in-the-wild image is a challenging ill-posed problem, primarily hindered by the scarc

In this post, we show how pairing Amazon Nova 2 Lite with Anthropic’s Claude Sonnet 4.6 delivers an efficient solution for digitizing scanned documents at scale. We built a two-model pipeline on Amazo

arXiv:2606.28252v1 Announce Type: cross Abstract: Early detection of oral cancer markedly improves clinical outcomes, yet specialized diagnostic tools remain scarce in low-resource settings. Smartphon

arXiv:2606.27821v1 Announce Type: cross Abstract: Traffic matrices (TMs) capture network-wide origin-destination demand and are central to traffic engineering, yet accurate whole-matrix forecasting re

arXiv:2606.28128v1 Announce Type: cross Abstract: Video generation models have emerged as a promising paradigm for embodied world simulation. However, both general-domain video generators and robot-sp

arXiv:2606.27449v1 Announce Type: new Abstract: Multi-head attention conventionally partitions the hidden dimension equally across all heads at every layer, enforcing an identical representational sub

arXiv:2509.03704v2 Announce Type: replace Abstract: Cooperative perception through Vehicle-to-Everything (V2X) communication offers significant potential for enhancing vehicle perception by mitigating

arXiv:2606.27385v1 Announce Type: cross Abstract: The most widely used RANSAC variants score candidate models by counting inliers or summing per-point scores that saturate beyond a residual threshold.

arXiv:2606.27967v1 Announce Type: new Abstract: Real-world knowledge graphs are often incomplete, lacking many valid facts. Knowledge Graph Completion (KGC) aims to predict missing links using known t

arXiv:2606.27766v1 Announce Type: cross Abstract: Offline reinforcement learning enables policy learning from fixed datasets without additional environment interaction, making it appealing for safety-

arXiv:2606.27908v1 Announce Type: new Abstract: Long-term time series forecasting finds extensive applications in domains such as power demand, traffic flow, meteorological observation, and renewable

arXiv:2606.28061v1 Announce Type: cross Abstract: Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments

arXiv:2506.10355v2 Announce Type: replace Abstract: Many real-world applications collect data in a streaming environment, where learning tasks are encountered sequentially. This necessitates continual

arXiv:2606.28117v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become the standard tool for parameter-efficient fine-tuning of large pretrained models. When applied sequentially across

Ethan Mollick raises questions about whether Google's Gemini 3.5 Pro model should be subject to export controls, suggesting concerns about its capabilities and potential regulatory implications. The p

Like if you have been using Qwen & Kimi & MiniMax, it feels like GLM is right on the curve. Which is itself impressive, and suggests that Mythos class models are coming in 6-12 months (if they are all

Llama.cpp has merged DFLASH support into its main branch, which is a development update related to optimization or acceleration technology for running large language models locally. The post expresses

The more serious answer @emollick I actually wouldn't be surprised if we're generally in an AI model release moratorium (regardless of capabilities) until the cybersecurity benchmark is finalized. Not

America is about to lose the AI race, and it will not happen at the frontier. It will happen at the floor. Everyone is watching who ships the smartest model. The actual war is over the 80% of tokens n

An interesting way to take Noam at his word in regards to always keeping a constant inference budget for any eval reporting - is that open models have a lot more dollar per token mileage than closed m

Sakana AI's Fugu-Ultra model is now available through Vercel's AI Gateway, expanding access to this language model through Vercel's infrastructure. This integration allows developers to use Fugu-Ultra

arXiv:2606.26627v1 Announce Type: cross Abstract: Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a us

arXiv:2606.26460v1 Announce Type: new Abstract: AI-based scientific automation is increasingly possible by using agents to generate hypotheses, design experiments, and analyze data. Data collection is

arXiv:2606.26155v1 Announce Type: new Abstract: Interpreting and controlling model behaviors through activation steering methods requires many pairs of contrastive samples that clearly exhibit desired