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
74.59/100
前 1.9%
全站排名 #1,252
发表论文24 篇
平均评分
年均产出8.0 篇/年
Bhavya Kailkhura
研究方向
Uncertainty in machine learning · Statistical signal processing · Adversarial machine learning · AI Safety and Security
19
UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Decision-Making
ICLR 2026Withdrawn
20
Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness
ICLR 2026Poster
18
A Comedy of Estimators: On KL Regularization in RL Training of LLMs
ICLR 2026Rejected
27
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
ICLR 2026Rejected
19
Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models
ICLR 2026Rejected
7
AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security
ICLR 2026Rejected
11
Scalable Pretraining of Retrieval Models
ICLR 2026Rejected
17
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
NeurIPS 2025Spotlight
21
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
NeurIPS 2025Poster
通讯17
ELFS: Label-Free Coreset Selection with Proxy Training Dynamics
ICLR 2025Poster
28
Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness
NeurIPS 2025Rejected
36
Constrained Discrete Diffusion
NeurIPS 2025Poster
三作22
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
NeurIPS 2025Poster
24
When SNN meets ANN: Error-Free ANN-to-SNN Conversion for Extreme Edge Efficiency
ICLR 2025Withdrawn
19
LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
COLM 2025Poster