Xue Liu

Span-level hallucination detection can now effectively address structured inputs like code and tool outputs, not just natural language, revealing a critical gap in current RAG evaluations.

Intermediate embeddings in distributed MLLM frameworks can leak sensitive image prompts, with new attacks achieving 100% extraction accuracy and revealing serious privacy implications.

Even state-of-the-art vision-language models frequently lie and hallucinate when playing social deduction games, raising serious questions about their reliability in real-world applications requiring grounded reasoning.

Seedance 2.0 leapfrogs existing models by unifying multi-modal inputs (text, image, audio, video) into a single architecture for generating high-quality, longer-duration audio-video content.

Stop overpaying for LLM serving: intelligently routing requests to specialized pools based on token budget slashes GPU costs by up to 42% and dramatically improves reliability.