Tao Wang
7 papers · Latest:
Risk-Controlled Post-Processing of Decision Policies
This paper introduces risk-controlled post-processing for decision policies, maximizing agreement with baselines under specified risk constraints.
Q-ARE: An Evaluation Dataset for Query Based API Recommendation
Q-ARE is a new dataset and metrics for evaluating query-based API recommendation methods, revealing struggles with multi-level invocations.
Kwai Summary Attention Technical Report
Kwai Summary Attention (KSA) reduces LLM long-context modeling costs by compressing historical contexts into learnable summary tokens.
Quiescent fractions in high-redshift galaxy groups reflect their hot-or-cold state of gas accretion
High-redshift galaxy groups show quiescent fractions linked to hot vs. cold gas accretion, suggesting environment drives galaxy quenching.
SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation
SpeechParaling-Bench is a new benchmark for evaluating paralinguistic-aware speech generation in LALMs, using fine-grained features and a novel LALM-based judge.
Photometric Metallicities for 367,324 stars of Omega Centauri
Researchers developed a method to derive photometric metallicities for over 367,000 stars in Omega Centauri, revealing insights into its stellar mixing.
Gemini: A Family of Highly Capable Multimodal Models
Gemini is a new family of multimodal AI models excelling in image, audio, video, and text understanding, achieving state-of-the-art results across numerous benchmarks including human-expert level on MMLU.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.