Hao Liang

RayOrch is presented, a programming model and distributed execution engine that preserves parent child relations throughout execution and reduces end to end time by 13.1 percent versus Ray Data and 29.0 percent versus Daft on MinerU, and by 16.0 percent versus Ray Data on Docling.

Current multimodal models falter in maintaining consistent motivation reasoning across sequences, exposing a critical gap in their social intelligence capabilities.

Agents excel at selecting knowledge sources but struggle with actual task completion, achieving only 56.1-75.3% accuracy in answers despite near-perfect routing.

Bridging the NL2Pipeline gap, DataFlow-Harness enables LLMs to create reliable, editable data workflows at a fraction of the cost and time of traditional methods.

Even state-of-the-art models only achieve pass rates below 60% on a new benchmark that spans 1,431 diverse tasks, exposing critical weaknesses in general AI capabilities.

Physically aligned video models can boost robotic manipulation success rates by over 50% compared to traditional methods.

Beyond a certain threshold, queue peaks grow logarithmically rather than quadratically, fundamentally altering our understanding of scheduling efficiency in stochastic networks.

Ditching text-based chain-of-thought unlocks better audio-visual reasoning by interleaving textual steps with a unified latent space that preserves dense sensory information.

LLMs can now be benchmarked for their ability to prepare training data, revealing that a new evaluation metric outperforms traditional methods in predicting downstream utility.

Stop wrestling with finicky evaluation codebases: One-Eval lets you specify LLM evaluation tasks in natural language and automatically executes them end-to-end.