31 citations · 93 across the 30 of their papers we have counts for
35 papers
Structuring MoE Expert Selection for Agentic Reinforcement Learning
Bolian Li, Ting-Yao Hu, Cheng-Yu Hsieh +3
Long-horizon LLM agents are frequently implemented using sparse mixture-of-experts (MoE) models, yet the co-design of agentic behavior and MoE structures remains underexplored. In…
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…
ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context
Zidi Xiu, David Q. Sun, Kevin Cheng +9
Next-generation AI must manage vast personal data, diverse tools, and multi-step reasoning, yet most benchmarks remain context-free and single-turn. We present ASTRA-bench (Assista…
Learning from Self Critique and Refinement for Faithful LLM Summarization
Ting-Yao Hu, Hema Swetha Koppula, Hadi Pouransari +3
Large Language Models (LLMs) often suffer from hallucinations: output content that is not grounded in the input context, when performing long-form text generation tasks such as sum…
AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding
Sanjoy Chowdhury, Karren D. Yang, Xudong Liu +6
Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in multi-speaker, dialogue-centric settings that demand agentic re…
Learning to Reason for Hallucination Span Detection
Hsuan Su, Ting-Yao Hu, Hema Swetha Koppula +7
Large language models (LLMs) often generate hallucinations -- unsupported content that undermines reliability. While most prior works frame hallucination detection as a binary task…
COMPASS: Benchmarking Constrained Optimization in LLM Agents
Tian Qin, Felix Bai, Ting-Yao Hu +8
Human decision-making often involves constrained optimization. As LLM agents are deployed to assist with real-world tasks like travel planning, shopping, and scheduling, they must…
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
Chen Huang, Skyler Seto, Hadi Pouransari +6
Vision foundation models pre-trained on massive data encode rich representations of real-world concepts, which can be adapted to downstream tasks by fine-tuning. However, fine-tuni…
FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations
Cheng-Yu Hsieh, Pavan Kumar Anasosalu Vasu, Fartash Faghri +5
Visual understanding is inherently contextual -- what we focus on in an image depends on the task at hand. For instance, given an image of a person holding a bouquet of flowers, we…
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining
Jeffrey Li, Mohammadreza Armandpour, Iman Mirzadeh +8
Large Language Models (LLMs) trained on historical web data inevitably become outdated. We investigate evaluation strategies and update methods for LLMs as new data becomes availab…
LangDA: Building Context-Awareness via Language for Domain Adaptive Semantic Segmentation
Chang Liu, Bavesh Balaji, Saad Hossain +5
Unsupervised domain adaptation for semantic segmentation (DASS) aims to transfer knowledge from a label-rich source domain to a target domain with no labels. Two key approaches in…
Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization
Yen-Ju Lu, Ting-Yao Hu, Hema Swetha Koppula +8
In this work, we propose Mutual Reinforcing Data Synthesis (MRDS) within LLMs to improve few-shot dialogue summarization task. Unlike prior methods that require external knowledge,…
Synth4Seg -- Learning Defect Data Synthesis for Defect Segmentation using Bi-level Optimization
Shancong Mou, Raviteja Vemulapalli, Shiyu Li +8
Defect segmentation is crucial for quality control in advanced manufacturing, yet data scarcity poses challenges for state-of-the-art supervised deep learning. Synthetic defect dat…
MUSCLE: A Model Update Strategy for Compatible LLM Evolution
Jessica Echterhoff, Fartash Faghri, Raviteja Vemulapalli +4
Large Language Models (LLMs) are regularly updated to enhance performance, typically through changes in data or architecture. Within the update process, developers often prioritize…
Weight subcloning: direct initialization of transformers using larger pretrained ones
Mohammad Samragh, Mehrdad Farajtabar, Sachin Mehta +5
Training large transformer models from scratch for a target task requires lots of data and is computationally demanding. The usual practice of transfer learning overcomes this chal…
Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications
Karren D. Yang, Anurag Ranjan, Jen-Hao Rick Chang +2
We consider the task of animating 3D facial geometry from speech signal. Existing works are primarily deterministic, focusing on learning a one-to-one mapping from speech signal to…
Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models
Raviteja Vemulapalli, Hadi Pouransari, Fartash Faghri +4
Vision Foundation Models (VFMs) pretrained on massive datasets exhibit impressive performance on various downstream tasks, especially with limited labeled target data. However, due…
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri +2
Contrastive pretraining of image-text foundation models, such as CLIP, demonstrated excellent zero-shot performance and improved robustness on a wide range of downstream tasks. How…
CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement
Mohammadreza Salehi, Mehrdad Farajtabar, Maxwell Horton +7
Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. While CLIP is scalable, promptable, and robust to distribution shifts on ima…
TiC-CLIP: Continual Training of CLIP Models
Saurabh Garg, Mehrdad Farajtabar, Hadi Pouransari +5
Keeping large foundation models up to date on latest data is inherently expensive. To avoid the prohibitive costs of constantly retraining, it is imperative to continually train th…
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri +6
The landscape of publicly available vision foundation models (VFMs), such as CLIP and Segment Anything Model (SAM), is expanding rapidly. VFMs are endowed with distinct capabilitie…
Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models
Hsuan Su, Ting-Yao Hu, Hema Swetha Koppula +5
While Automatic Speech Recognition (ASR) systems are widely used in many real-world applications, they often do not generalize well to new domains and need to be finetuned on data…
Towards Federated Learning Under Resource Constraints via Layer-wise Training and Depth Dropout
Pengfei Guo, Warren Richard Morningstar, Raviteja Vemulapalli +3
Large machine learning models trained on diverse data have recently seen unprecedented success. Federated learning enables training on private data that may otherwise be inaccessib…
Federated Training of Dual Encoding Models on Small Non-IID Client Datasets
Raviteja Vemulapalli, Warren Richard Morningstar, Philip Andrew Mansfield +4
Dual encoding models that encode a pair of inputs are widely used for representation learning. Many approaches train dual encoding models by maximizing agreement between pairs of e…