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
31.29/100
前 23%
全站排名 #14,819
发表论文11 篇
平均评分
年均产出3.7 篇/年
Radha Poovendran
研究方向
Multi-Agent Systems · Adversarial AI · Reinforcement Learning · Game Theory · LLM · LRM · Synthetic Data · Datasets · Security
32
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
ICLR 2026Rejected
28
TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
ICLR 2026Rejected
25
SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
ICLR 2026Poster
通讯5
Steering Multimodal Large Language Models Decoding for Context-Aware Safety
ICLR 2026Withdrawn
-1
Simulating Environments with Large Language Models for Generic Agent Training
ICLR 2026Desk Rejected
-1
Temporal Sampling for Forgotten Reasoning in LLMs
ICLR 2026Desk Rejected
通讯