Large Language Models

Zoom + Claude Connector

Zoom have just launched their Claude Connector bringing a whole host of data & information into your Claude workspace. As a Claude Co...

Must your chatbot rat you out?

New court cases may take chatbot conversations another step away from privacy You may recall that court cases have recently held users’ c...

[2512.07703] PVeRA: Probabilistic Vector-Based Random Matrix Adaptation

Abstract page for arXiv paper 2512.07703: PVeRA: Probabilistic Vector-Based Random Matrix Adaptation

Raycast’s Glaze is an all-in-one app platform for vibe coders | The Verge

Using models like Claude Code and Codex, Glaze tries to make it easier than ever to create apps with a simple prompt. Users can even shar...

I’m a college admissions counselor. I’ve changed my mind about students using ChatGPT

What is your stack to maintain Knowledge base for your AI workflows?

I was wondering what to use to streamline all my md files from my claude code plans and the technical docs I create. How will it work in ...

Open-source AI tool beats giant LLMs in literature reviews — and gets citations right

A new open-source AI model outperforms major large language models in literature reviews, achieving citation accuracy comparable to human...

Wix ChatGPT Integration Puts AI Website Creation At Center Of Growth Story

[2512.06227] Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety

Abstract page for arXiv paper 2512.06227: Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for...

[2510.08946] Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection

Abstract page for arXiv paper 2510.08946: Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection

[2510.03215] Cache-to-Cache: Direct Semantic Communication Between Large Language Models

Abstract page for arXiv paper 2510.03215: Cache-to-Cache: Direct Semantic Communication Between Large Language Models

[2506.05334] Search Arena: Analyzing Search-Augmented LLMs

Abstract page for arXiv paper 2506.05334: Search Arena: Analyzing Search-Augmented LLMs

[2505.05619] LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilities

Abstract page for arXiv paper 2505.05619: LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Languag...

[2404.02138] Topic-Based Watermarks for Large Language Models

Abstract page for arXiv paper 2404.02138: Topic-Based Watermarks for Large Language Models

[2602.04288] Contextual Drag: How Errors in the Context Affect LLM Reasoning

Abstract page for arXiv paper 2602.04288: Contextual Drag: How Errors in the Context Affect LLM Reasoning

[2601.09566] Hot-Start from Pixels: Low-Resolution Visual Tokens for Chinese Language Modeling

Abstract page for arXiv paper 2601.09566: Hot-Start from Pixels: Low-Resolution Visual Tokens for Chinese Language Modeling

[2511.12832] From Passive to Persuasive: Steering Emotional Nuance in Human-AI Negotiation

Abstract page for arXiv paper 2511.12832: From Passive to Persuasive: Steering Emotional Nuance in Human-AI Negotiation

[2510.14686] xLLM Technical Report

Abstract page for arXiv paper 2510.14686: xLLM Technical Report

[2510.14086] Every Language Model Has a Forgery-Resistant Signature

Abstract page for arXiv paper 2510.14086: Every Language Model Has a Forgery-Resistant Signature

[2510.13900] Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences

Abstract page for arXiv paper 2510.13900: Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences

[2510.13315] Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models

Abstract page for arXiv paper 2510.13315: Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models

[2510.06084] Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability

Abstract page for arXiv paper 2510.06084: Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability

[2509.22641] Death of the Novel(ty): Beyond n-Gram Novelty as a Metric for Textual Creativity

Abstract page for arXiv paper 2509.22641: Death of the Novel(ty): Beyond n-Gram Novelty as a Metric for Textual Creativity