影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
-/100
发表论文5 篇
平均评分
年均产出2.5 篇/年
Minghui Liu
研究方向
LLM reasoning · RLHF · RLVR · process reward models · diffusion language models · efficient llm · kv cache compression · inference time optimization · quantization · event camera · spiking neural networks
11
Hold Onto That Thought: Assessing KV Cache Compression On Reasoning
ICLR 2026Rejected
一作16
PersonaLedger: Generating Realistic Financial Transactions with Persona Conditioned LLMs and Rule Grounded Feedback
ICLR 2026Rejected
三作17
Ladders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces
ICLR 2026Rejected
一作5
MORSE: A Suite of Programmatically Controllable Multimodal Reasoning Environments with Steerable Difficulty
ICLR 2026Desk Rejected