Opinions
The AI Race Could Sink US-China Détente
Ian Bremmer argues that AI competition between the United States and China is now the single greatest threat to their…
Opinions
AI’s Market Path Will Get Bumpier
Mohamed A. El-Erian argues that the US economy faces a tension between AI’s potential to lift productivity by enhancing intelligence…
Opinions
BREAKING: Two rays of hope
Gary Marcus highlights two developments he says advance AI transparency: Senator Richard Blumenthal’s letter demanding OpenAI disclose details about its…
Engineering
HyQuant: Hybrid-Precision Quantization for LLM Attention
HyQuant is a hybrid-precision quantization framework that addresses accuracy loss in low-bit quantization of LLM attention by selectively keeping high…
Engineering
Auto-RecSys: Harnessing Autonomous Research Agents for Industry-Scale Recommender Systems
The paper presents Auto-RecSys, an autonomous research-agent system for running large-scale recommender-system experimentation, using distributed asynchronous execution to run multiple…
Engineering
SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs
SearchAtlas is a framework that converts raw search trajectories produced by LLM agents into structured evidence graphs showing how evidence…
Engineering
RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety
The paper introduces RAG-Safety-Bench, a benchmark isolating how retrieval-augmented generation affects LLM safety by testing four controlled conditions: no-RAG baseline…
Engineering
LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation
The paper introduces LOCUS, a post-training method that curbs verbosity in large language models by applying task-aware low-rank adaptations that…
Engineering
Structured Transforms for Low-Overhead Quantization of Language Models
Researchers present an enhanced quantization method for large language models that improves on Kashin-decomposition-based approaches by replacing dense random orthogonal…
Engineering
vLLM x AgentX: Optimizing for Real-World Agentic Serving
The post describes a three-layer stack vLLM uses to optimize serving for agentic workloads: a data plane with hybrid KV…
Engineering
Tiered KV Cache Offloading in vLLM
vLLM’s tiered KV cache offloading system preserves evicted key-value cache data across host memory, storage, and remote peers instead of…
Engineering
An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics
The paper details training Nemotron 3 Ultra with supervised fine-tuning and reinforcement learning to produce natural-language mathematical proofs, built around…