💡 AI Reasoning - yfff · Scour

Tight Sample Complexity of Transformers

✍️Prompt Engineering Academic

SafeRun: Enabling Determinism in LLM Planning for Running

💬LLMs Academic

Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning

🎮Reinforcement Learning Academic

Latent Reasoning with Normalizing Flows

✍️Prompt Engineering Academic

The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models

💬LLMs Academic

avibe-bot/avibe: The local-first Agent OS — your AI partner lives on your own machine. Drive the official Claude Code, Codex & OpenCode from your browser or any chat app.

⌨️CLI Tools Code

github.com··Hacker News

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It

✍️Prompt Engineering Academic

SSR: Can Simulated Patients Learn to Stigmatize Themselves? Modeling Self-Stigma through Internal Monologue

✍️Prompt Engineering Academic

LoRi: Low-Rank Distillation for Implicit Reasoning

✍️Prompt Engineering Academic

Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems

✍️Prompt Engineering Academic

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

✍️Prompt Engineering Academic

You Only Index Once: Cross-Layer Sparse Attention with Shared Routing

✍️Prompt Engineering Academic

When No Answer Is Correct: Diagnosing Absent Answer Detection for MLLMs in Video Understanding

✍️Prompt Engineering Academic

BEACON: Behavioral Entropy Aggregation for Cross-Model Hallucination Detection in Large Language Models

✍️Prompt Engineering Academic

MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action

✍️Prompt Engineering Academic

Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation

✍️Prompt Engineering Academic

How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions

💬LLMs Academic

Arithmetic Pedagogy for Language Models

✍️Prompt Engineering Academic

arxiv.org··Hacker News

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization

✍️Prompt Engineering Academic

The Granularity Gap: A Multi-Dimensional Longitudinal Audit of Sycophancy in Gemini Models

✍️Prompt Engineering Academic

No more posts from yfff's subscribed feeds.

Scour all 25258 feeds Learn more about Feeds

Log in to enable infinite scrolling