Souradip Chakraborty
~Souradip_Chakraborty1
15
论文总数
7.5
年均投稿
平均评分
接收情况7/15
会议分布
ICLR
11
NeurIPS
3
ICML
1
发表论文 (15 篇)
202511 篇
4
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
ICLR 2025Poster
4
SAIL: Self-improving Efficient Online Alignment of Large Language Models
ICLR 2025Rejected
4
AIME: AI System Optimization via Multiple LLM Evaluators
ICLR 2025withdrawn
4
On the Sample Complexity of a Policy Gradient Algorithm with Occupancy Approximation for General Utility Reinforcement Learning
ICLR 2025Rejected
4
DIPPER: Direct Preference Optimization for Primitive-Enabled Hierarchical Reinforcement Learning
ICLR 2025withdrawn
4
On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
NeurIPS 2025Poster
5
LIAR: Leveraging Inverse Alignment to Jailbreak LLMs in Seconds
ICLR 2025Rejected
4
Hierarchical Preference Optimization: Learning to achieve goals via feasible subgoals prediction
ICLR 2025withdrawn
4
Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
NeurIPS 2025Poster
4
Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
ICML 2025Poster
4
Aligning Large Language Models With Preference Privacy
ICLR 2025Rejected
20244 篇
4
PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
ICLR 2024Poster
4
Transfer Q-star : Principled Decoding for LLM Alignment
NeurIPS 2024Poster
4
On the Possibilities of AI-Generated Text Detection: A Sample Complexity Analysis
ICLR 2024Rejected
4
Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
ICLR 2024Poster