21 citations · 43 across the 30 of their papers we have counts for
33 papers
Simulate to Generalize: Scaling Stateful Supervision for API-calling Agents using LLM World Models
Seanie Lee, Sanjoy Chowdhury, Chao Jiang +5
Training agents that generalize to unseen, stateful environments requires a massive dataset of state-changing trajectories covering a vast and diverse set of APIs. However, scaling…
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
Sangwoo Park, Woongyeong Yeo, Seanie Lee +6
Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language…
T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
Hyomin Lee, Sangwoo Park, Yumin Choi +3
While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capture agent-specific vulnerabilities tha…
THINKSAFE: Self-Generated Safety Alignment for Reasoning Models
Seanie Lee, Sangwoo Park, Yumin Choi +6
Large reasoning models (LRMs) achieve remarkable performance by leveraging reinforcement learning (RL) on reasoning tasks to generate long chain-of-thought (CoT) reasoning. However…
Rethinking Reward Models for Multi-Domain Test-Time Scaling
Dong Bok Lee, Seanie Lee, Sangwoo Park +12
The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning…
HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model
Youngwan Lee, Kangsan Kim, Kwanyong Park +5
Despite emerging efforts to enhance the safety of Vision-Language Models (VLMs), current approaches face two main shortcomings. 1) Existing safety-tuning datasets and benchmarks on…
Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition
Dominik Wagner, Ilja Baumann, Natalie Engert +4
In this work, we present our submission to the Speech Accessibility Project challenge for dysarthric speech recognition. We integrate parameter-efficient fine-tuning with latent au…
Distilling LLM Agent into Small Models with Retrieval and Code Tools
Minki Kang, Jongwon Jeong, Seanie Lee +2
Large language models (LLMs) excel at complex reasoning tasks but remain computationally expensive, limiting their practical deployment. To address this, recent works have focused…
FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA
Seanie Lee, Sangwoo Park, Dong Bok Lee +5
Low-Rank Adaptation (LoRA), which introduces a product of two trainable low-rank matrices into frozen pre-trained weights, is widely used for efficient fine-tuning of language mode…
FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates
Sangwoo Park, Seanie Lee, Byungjoo Kim +1
Federated Learning (FL) is a widely used framework for training models in a decentralized manner, ensuring that the central server does not have direct access to data from local cl…
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
Brian Bartoldson, Siddarth Venkatraman, James Diffenderfer +7
Reinforcement learning (RL) is a critical component of large language model (LLM) post-training. However, on-policy algorithms used for post-training are not naturally robust to a…
SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
Seanie Lee, Dong Bok Lee, Dominik Wagner +5
Deploying large language models (LLMs) in real-world applications requires robust safety guard models to detect and block harmful user prompts. While large safety guard models achi…
Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation
Chaeyun Jang, Deukhwan Cho, Seanie Lee +2
Recently, Large Language Models (LLMs) have been increasingly used to support various decision-making tasks, assisting humans in making informed decisions. However, when LLMs confi…
HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
Seanie Lee, Haebin Seong, Dong Bok Lee +6
Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world appli…
Optimized Speculative Sampling for GPU Hardware Accelerators
Dominik Wagner, Seanie Lee, Ilja Baumann +3
In this work, we optimize speculative sampling for parallel hardware accelerators to improve sampling speed. We notice that substantial portions of the intermediate matrices necess…
Learning diverse attacks on large language models for robust red-teaming and safety tuning
Seanie Lee, Minsu Kim, Lynn Cherif +8
Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large language models (LLMs). Developing ef…
Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries
Seanie Lee, Jianpeng Cheng, Joris Driesen +2
Few-shot dialogue state tracking (DST) with Large Language Models (LLM) relies on an effective and efficient conversation retriever to find similar in-context examples for prompt l…
Self-Supervised Dataset Distillation for Transfer Learning
Dong Bok Lee, Seanie Lee, Joonho Ko +3
Dataset distillation methods have achieved remarkable success in distilling a large dataset into a small set of representative samples. However, they are not designed to produce a…
Drug Discovery with Dynamic Goal-aware Fragments
Seul Lee, Seanie Lee, Kenji Kawaguchi +1
Fragment-based drug discovery is an effective strategy for discovering drug candidates in the vast chemical space, and has been widely employed in molecular generative models. Howe…
Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks
Minki Kang, Seanie Lee, Jinheon Baek +2
Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks that require a compound understanding of knowledge. However, deployment of the…
DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
Sohyun An, Hayeon Lee, Jaehyeong Jo +2
Existing NAS methods suffer from either an excessive amount of time for repetitive sampling and training of many task-irrelevant architectures. To tackle such limitations of existi…
On Divergence Measures for Bayesian Pseudocoresets
Balhae Kim, Jungwon Choi, Seanie Lee +3
A Bayesian pseudocoreset is a small synthetic dataset for which the posterior over parameters approximates that of the original dataset. While promising, the scalability of Bayesia…
Self-Distillation for Further Pre-training of Transformers
Seanie Lee, Minki Kang, Juho Lee +2
Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strat…
Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation
Jeffrey Willette, Seanie Lee, Bruno Andreis +3
Recent work on mini-batch consistency (MBC) for set functions has brought attention to the need for sequentially processing and aggregating chunks of a partitioned set while guaran…