🤖 AI - yfff · Scour

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation

💬LLMs Academic

What Do People Actually Want From AI? Mapping Preference Plurality

🧠LLM Academic

princezuda/-RequiemGPT-: Fully open source and open weights built and trained by fable five with one prompt. An experience in how AI actually works

🤖Transformers Code

github.com··Hacker News

Overcoming Rank Collapse in Feedback Alignment

📐Linear Algebra Academic

[AINews] not much happened today

💬LLMs News

·

Hidden Consensus:Preference-Validity Compression in Human Feedback

🎮Reinforcement Learning Academic

Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning

🧠Machine Learning Academic

Breaking the Ice: Analyzing Cold Start Latency in vLLM

💬LLMs Academic

arxiv.org··Hacker News

Thousand Token Wood: shipping a multi-agent economy on a 3B model

🕵️LLM Agents Blog

huggingface.co·

chipmates/agoracosmica: A Living Library You Can Talk To. Open-source educational platform with 30 historical figures from philosophy, science, art, mysticism, and activism. Stories, dialogues, AI conversation, multi-figure councils. Nonprofit, BYOK, self-hostable, no behavioral tracking.

💾Retro Computing Code

github.com··Hacker News

Principled Agent Debate: Adversarial Arbitration for Sycophancy Reduction in Large Language Models

🎮Reinforcement Learning Academic

Towards Tight Bounds for Streaming Attention

🤖Transformers Academic

Nvidia DGX Spark GB10 – AI Models and Guide with vLLM and Autonomous Script

💬LLMs Code

github.com··Hacker News

Perturbative Contrastive Physical Learning

🧠Machine Learning Academic

Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training

🧠Machine Learning Academic

KJLdefeated/RL.cu: RLVR training for LLM in CUDA/C++

🧠Machine Learning Code

github.com··Hacker News

Q-VGM: Q-Guided Value-Gradient Matching for Flow-Matching VLA Policies

🎮Reinforcement Learning Academic

Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation

🧠Machine Learning Academic

Phantom transitions in language model fine-tuning

🧠Machine Learning Academic

Show HN: CLI for scoring OpenAPI for LLM legibility

⌨️CLI Tools Code

github.com··Hacker News

No more posts from yfff's subscribed feeds.

Scour all 25257 feeds Learn more about Feeds

Sign up or log in to see more results

Log in to enable infinite scrolling