3 papers
cs.CV2025
MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading
Wenhao Zhang, Jun Wang, Yong Luo +4
Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different fra…
cs.SE2024
: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding
Shuai Wang, Liang Ding, Li Shen +4
Large language models (LLMs) have shown remarkable capabilities in code generation. However, the effects of hallucinations (e.g., output noise) make it particularly challenging for…
cs.LG2024
Joint Input and Output Coordination for Class-Incremental Learning
Shuai Wang, Yibing Zhan, Yong Luo +4
Incremental learning is nontrivial due to severe catastrophic forgetting. Although storing a small amount of data on old tasks during incremental learning is a feasible solution, c…