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
63.64/100
前 3.8%
全站排名 #2,470
发表论文14 篇
平均评分
年均产出4.7 篇/年
Tim Rocktäschel
研究方向
Artificial Intelligence · Open-Endedness · Reinforcement Learning · Self-Improvement
26
Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs
ICLR 2026Poster
15
DéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems
ICLR 2026Rejected
17
Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
ICLR 2026Rejected
通讯15
LLM-First Search: Self-Guided Exploration of the Solution Space
ICLR 2026Rejected
二作12
Investigating Non-Transitivity in LLM-as-a-Judge
ICML 2025Spotlight
三作25
Imagined Autocurricula
NeurIPS 2025Poster
29
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
ICLR 2025Poster
30
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
ICLR 2025Poster
通讯25
TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation
ICLR 2025Rejected
二作26
Towards Learning to Reason at Pre-Training Scale
ICLR 2025Rejected