54 citations · 79 across the 50 of their papers we have counts for
51 papers
FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse
Lingzhi Yuan, Chenghao Deng, Fangxu Yu +3
Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off. Task-level metho…
Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models
Prajakta Kini, Avinash Reddy, Souradip Chakraborty +4
Instruction-tuned LLMs are increasingly converted into reasoning models through post-training to improve multi-step task performance. This conversion is usually optimized for reaso…
The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning
Aakriti Agrawal, Souradip Chakraborty, Armin Saghafian +6
Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback. However, we identify a hidden bias in PRMs caused by severe imbalance in step…
RL with Learnable Textual Feedback: A Bilevel Approach
Utsav Singh, Sidhaarth Sredharan, Souradip Chakraborty +1
Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning remains sample-inefficient when terminal rewards are sparse. This has motivated a growing lin…
Agentic Critical Training
Weize Liu, Minghui Liu, Sy-Tuyen Ho +5
Imitation learning (IL) teaches language-model agents to reproduce expert actions but not to distinguish them from plausible mistakes. Self-reflection methods expose models to alte…
Prompt Interference in LLM Post-Training: Why Pass@k Optimization Can Degrade Pass@1
Anas Barakat, Souradip Chakraborty, Khushbu Pahwa +1
Pass@ is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-answer reasoning. It defines su…
Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
Soumya Suvra Ghosal, Souradip Chakraborty, Vaibhav Singh +3
Reinforcement learning (RL) based post-training for explicit chain-of-thought (e.g., GRPO) improves the reasoning ability of multimodal large-scale reasoning models (MLRMs). But re…
Generative AI for Biosciences: Emerging Threats and Roadmap to Biosecurity
Zaixi Zhang, Souradip Chakraborty, Amrit Singh Bedi +16
The rapid adoption of generative artificial intelligence (GenAI) in the biosciences is transforming biotechnology, medicine, and synthetic biology. Yet this advancement is intrinsi…
Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts
Jihoon Lee, Hoyeon Moon, Kevin Zhai +6
Diffusion-based large language models (dLLMs) are trained flexibly to model extreme dependence in the data distribution; however, how to best utilize this information at inference…
MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models
Kevin Zhai, Utsav Singh, Anirudh Thatipelli +5
Diffusion models excel at generating images conditioned on text prompts, but the resulting images often do not satisfy user-specific criteria measured by scalar rewards such as Aes…
Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
Aakriti Agrawal, Rohith Aralikatti, Anirudh Satheesh +3
Large Language Models (LLMs) have demonstrated exceptional capabilities, yet selecting the most reliable response from multiple LLMs remains a challenge, particularly in resource-c…
HEART: Emotionally-Driven Test-Time Scaling of Language Models
Gabriela Pinto, Palash Goyal, Mihir Parmar +6
Test-time scaling has significantly improved how AI models solve problems, yet current methods often get stuck in repetitive, incorrect patterns of thought. We introduce HEART, a f…
Post-training Large Language Models for Diverse High-Quality Responses
Yilei Chen, Souradip Chakraborty, Lorenz Wolf +2
Reinforcement learning (RL) has emerged as a popular method for post-training large language models (LLMs). While improving the model's performance on downstream tasks, it often re…
PROPS: Progressively Private Self-alignment of Large Language Models
Noel Teku, Fengwei Tian, Payel Bhattacharjee +3
Alignment is a key step in developing Large Language Models (LLMs) using human feedback to ensure adherence to human values and societal norms. Dependence on human feedback raises…
Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models
Soumya Suvra Ghosal, Souradip Chakraborty, Avinash Reddy +6
Recent trends in test-time scaling for reasoning models (e.g., OpenAI o1, DeepSeek R1) have led to a popular belief that extending thinking traces using prompts like "Wait" or "Let…
Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
Mohamad Chehade, Soumya Suvra Ghosal, Souradip Chakraborty +4
Aligning large language models with humans is challenging due to the inherently multifaceted nature of preference feedback. While existing approaches typically frame this as a mult…
On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows
Souradip Chakraborty, Mohammadreza Pourreza, Ruoxi Sun +8
Agentic AI workflows (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low. A promising solution is inference-t…
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
Souradip Chakraborty, Sujay Bhatt, Udari Madhushani Sehwag +7
Alignment of Large Language models (LLMs) is crucial for safe and trustworthy deployment in applications. Reinforcement learning from human feedback (RLHF) has emerged as an effect…
VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences
Anukriti Singh, Amisha Bhaskar, Peihong Yu +4
Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of…
BalancedDPO: Adaptive Multi-Metric Alignment
Dipesh Tamboli, Souradip Chakraborty, Aditya Malusare +3
Diffusion models have achieved remarkable progress in text-to-image generation, yet aligning them with human preference remains challenging due to the presence of multiple, sometim…
Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
Prashant Trivedi, Souradip Chakraborty, Avinash Reddy +3
The alignment of large language models (LLMs) with human values is critical as these models become increasingly integrated into various societal and decision-making processes. Trad…
LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds
James Beetham, Souradip Chakraborty, Mengdi Wang +3
Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts. Existing methods rely on discrete optimization or tr…
Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
Soumya Suvra Ghosal, Souradip Chakraborty, Vaibhav Singh +7
With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that des…
Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach
Utsav Singh, Souradip Chakraborty, Wesley A. Suttle +6
Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However, HRL methods face two fundament…