LLM Research
DAJ: Data-Reweighted LLM Judges Improve Code Generation
New research introduces DAJ, a data-reweighting approach for LLM judges that improves test-time scaling in code generation by better identifying correct solutions.
Machine Learning
LLM Evaluation
Representation-as-a-Judge: Small Models Beat LLMs at Evaluation
New research reveals smaller language models can outperform large LLMs at evaluation tasks through semantic capacity asymmetry, challenging the dominant LLM-as-a-Judge paradigm.
AI Agents
Training Small AI Agents with Synthetic Worlds and Rubric Rewards
New research presents a framework for building capable small language model agents using synthetic tasks, simulated environments, and structured rubric-based rewards—democratizing agentic AI development.
LLM Security
Drunk Prompts: Novel Jailbreak Method Exposes LLM Safety Gaps
Researchers discover that simulating intoxicated speech patterns can bypass AI safety guardrails. The 'In Vino Veritas' attack reveals fundamental weaknesses in how LLMs handle linguistic degradation.
LoRA
LoRA Fine-Tuning: Run Massive AI Models on Consumer Hardware
Learn how Low-Rank Adaptation lets you customize billion-parameter AI models on standard laptops—the same technique powering custom deepfakes and AI video generation.
LLM Reasoning
Why Advanced AI Models Still Fail at Simple Logic Puzzles
New research reveals that even frontier AI models like GPT-4 and Claude struggle with basic reasoning puzzles, exposing fundamental limitations in how large language models process logic.
AI Benchmarks
FrontierScience Benchmark Tests AI on Expert Science Tasks
New benchmark evaluates whether frontier AI models can perform PhD-level scientific research tasks, revealing significant gaps between current capabilities and expert human performance.
AI Safety
Research Explores How Information Access Shapes AI Sabotage Detec
New arXiv research investigates how varying levels of information access affect LLM monitors' ability to detect sabotage, with implications for AI safety and oversight systems.
LLM Research
Policy of Thoughts: Evolving LLM Reasoning at Test Time
New research introduces test-time policy evolution to scale LLM reasoning without additional training, enabling models to dynamically improve their problem-solving strategies during inference.
AI systems
SETA: A New Framework for Debugging Multi-Component AI Systems
Researchers introduce SETA, a statistical method for identifying which component in complex AI pipelines causes failures—critical for debugging multi-stage systems like video generation workflows.
LLM Research
Process-Supervised RL: Precise Error Penalization Boosts LLM Reas
New research introduces a method to preserve correct reasoning steps while penalizing errors, improving LLM performance through more nuanced reinforcement learning credit assignment.
LLM Research
Activation Steering: How Reasoning-Critical Neurons Improve LLM R
New research identifies specific neurons responsible for reasoning in LLMs and demonstrates how transferring their activation patterns can significantly improve inference reliability across models.