Large Language Models

How to use the new ChatGPT app integrations, including DoorDash, Spotify, Uber, and others | TechCrunch

Learn how to use Spotify, Canva, Figma, Expedia, and other apps directly in ChatGPT.

Anthropic Restricts Claude Agent Access Amid AI Automation Boom in Crypto

Is cutting ‘please’ when talking to ChatGPT better for the planet? An expert explains

[2603.05026] RepoLaunch: Automating Build&Test Pipeline of Code Repositories on ANY Language and ANY Platform

Abstract page for arXiv paper 2603.05026: RepoLaunch: Automating Build&Test Pipeline of Code Repositories on ANY Language and ANY Platform

[2603.04964] Replaying pre-training data improves fine-tuning

Abstract page for arXiv paper 2603.04964: Replaying pre-training data improves fine-tuning

[2603.04716] SLO-Aware Compute Resource Allocation for Prefill-Decode Disaggregated LLM Inference

Abstract page for arXiv paper 2603.04716: SLO-Aware Compute Resource Allocation for Prefill-Decode Disaggregated LLM Inference

[2603.04480] AbAffinity: A Large Language Model for Predicting Antibody Binding Affinity against SARS-CoV-2

Abstract page for arXiv paper 2603.04480: AbAffinity: A Large Language Model for Predicting Antibody Binding Affinity against SARS-CoV-2

[2603.04466] Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation

Abstract page for arXiv paper 2603.04466: Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation

[2603.05232] SlideSparse: Fast and Flexible (2N-2):2N Structured Sparsity

Abstract page for arXiv paper 2603.05232: SlideSparse: Fast and Flexible (2N-2):2N Structured Sparsity

[2603.04972] Functionality-Oriented LLM Merging on the Fisher--Rao Manifold

Abstract page for arXiv paper 2603.04972: Functionality-Oriented LLM Merging on the Fisher--Rao Manifold

[2603.04956] WaterSIC: information-theoretically (near) optimal linear layer quantization

Abstract page for arXiv paper 2603.04956: WaterSIC: information-theoretically (near) optimal linear layer quantization

[2603.04948] $\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space

Abstract page for arXiv paper 2603.04948: $\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space

[2603.04898] U-Parking: Distributed UWB-Assisted Autonomous Parking System with Robust Localization and Intelligent Planning

Abstract page for arXiv paper 2603.04898: U-Parking: Distributed UWB-Assisted Autonomous Parking System with Robust Localization and Inte...

[2603.04851] Why Is RLHF Alignment Shallow? A Gradient Analysis

Abstract page for arXiv paper 2603.04851: Why Is RLHF Alignment Shallow? A Gradient Analysis

[2603.04692] Engineering Regression Without Real-Data Training: Domain Adaptation for Tabular Foundation Models Using Multi-Dataset Embeddings

Abstract page for arXiv paper 2603.04692: Engineering Regression Without Real-Data Training: Domain Adaptation for Tabular Foundation Mod...

[2603.04606] PDE foundation model-accelerated inverse estimation of system parameters in inertial confinement fusion

Abstract page for arXiv paper 2603.04606: PDE foundation model-accelerated inverse estimation of system parameters in inertial confinemen...

[2603.04545] An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs

Abstract page for arXiv paper 2603.04545: An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs

[2603.04478] Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teacher Distillation

Abstract page for arXiv paper 2603.04478: Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teac...

[2602.07075] LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

Abstract page for arXiv paper 2602.07075: LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

[2601.23236] YuriiFormer: A Suite of Nesterov-Accelerated Transformers

Abstract page for arXiv paper 2601.23236: YuriiFormer: A Suite of Nesterov-Accelerated Transformers

[2601.21149] Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human Movement

Abstract page for arXiv paper 2601.21149: Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human Movement

[2601.16333] Where is the multimodal goal post? On the Ability of Foundation Models to Recognize Contextually Important Moments

Abstract page for arXiv paper 2601.16333: Where is the multimodal goal post? On the Ability of Foundation Models to Recognize Contextuall...

[2601.14327] Yuan3.0 Ultra: A Trillion-Parameter Enterprise-Oriented MoE LLM

Abstract page for arXiv paper 2601.14327: Yuan3.0 Ultra: A Trillion-Parameter Enterprise-Oriented MoE LLM