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
15.89/100
超过 48.1%
全站排名 #33,411
发表论文12 篇
平均评分
年均产出6.0 篇/年
Chengwei Qin
研究方向
continual learning · few-shot learning · large language model · in-context learning · reasoning · efficient tuning
23
Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations
ICLR 2026Rejected
17
Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph
ICLR 2026Rejected
16
SafeReview: Building a Robust Deep Review Assistant Against Prompt Injection
ICLR 2026Rejected
34
Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models
ICLR 2026Poster
18
Interactive Learning for LLM Reasoning
ICLR 2026Withdrawn
通讯19
MGAL: A Multilingual Granularity-Aware Long-context Benchmark
ICLR 2026Withdrawn
通讯9
DRQA: Dynamic Reasoning Quota Allocation for Controlling Overthinking in Reasoning Large Language Models
ICLR 2026Withdrawn
通讯5
Self-Reflective Generation at Test Time
ICLR 2026Withdrawn
12
Beyond Unidirectional Flow: LLM Reasoning with Bidirectional Cycle-Consistent CoT
ICLR 2026Withdrawn
12
FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline
ICLR 2026Withdrawn
通讯