4 papers
FFMT: Frequency-Factorized Multi-Rate Tokenization for Music-to-Dance Generation
Qirong Guo, Ruijie Li, Zeyan Li +3
Dance motion combines slowly varying body configurations with rapid local movements. We investigate how explicit temporal-frequency decomposition can guide the temporal resolution…
SGAnalog: An End-to-End Circuit Benchmark from Open-Source Silicon Tapeouts
Yueting Li, Weihang Ding
Existing analog integrated circuit design benchmarks make two questions hard to answer: whether a model has learned transferable circuit skills rather than recalled familiar exampl…
FDE-Bench: Evaluating LLM Agents for Deployment Environment Configuration
Weihang Ding, Junfei Zhan, Yueting Li +1
Deployment requires an agent to turn application code into a running system whose services connect, become ready, and remain observable. FDE-Bench evaluates this capability with 13…
Trains but Doesn't Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers
Weihang Ding, Junfei Zhan
Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned, evaluated, and deployed model…