4 papers
ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
Zican Dong, Peiyu Liu, Junyi Li +4
Recently, large language models (LLMs) have shown remarkable reasoning abilities by producing long reasoning traces. However, as the sequence length grows, the key-value (KV) cache…
How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices
Han Peng, Peiyu Liu, Zican Dong +5
Diffusion language models (DLMs) have emerged as a promising alternative to the long-dominant autoregressive (AR) paradigm, offering a parallelable decoding process that could yiel…
Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations
Zican Dong, Han Peng, Peiyu Liu +4
Mixture-of-Experts (MoE) models achieve a favorable trade-off between performance and inference efficiency by activating only a subset of experts. However, the memory overhead of s…
CAFE: Retrieval Head-based Coarse-to-Fine Information Seeking to Enhance Multi-Document QA Capability
Han Peng, Jinhao Jiang, Zican Dong +2
Advancements in Large Language Models (LLMs) have extended their input context length, yet they still struggle with retrieval and reasoning in long-context inputs. Existing methods…