4 papers
Knowing Is Not Choosing: What Explicit Verification Adds Beyond Generative Preference
Yilong Li, Chengpo Yan, Aayan Arish +1
Generating a correct answer does not mean that a language model will select it. We separate factual recall into three steps: generating a correct candidate, ranking the available c…
EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents
Yilong Li, Suman Banerjee, Tong Che
Long-horizon agents can archive large histories, but future answers still incur retrieval, rereading, and context costs. When retained memory misses answer-relevant evidence, the s…
Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices
Yilong Li, Shuai Zhang, Yijing Zeng +5
Large Multimodal Models (LMMs) are inherently modular, comprising vision and audio encoders, a projector, and a language backbone. Yet existing systems execute them monolithically,…
PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
Yilong Li, Jingyu Liu, Hao Zhang +7
Deploying large language models (LLMs) locally on mobile devices is advantageous in scenarios where transmitting data to remote cloud servers is either undesirable due to privacy c…