2 citations · 3 across the 22 of their papers we have counts for
23 papers
When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts Models
Berkcan Kapusuzoglu, Connor Pryor, Sangwoo Cho +4
Expert pruning reduces the memory and serving cost of Mixture-of-Experts (MoE) models by removing low-importance experts identified by the router, assuming router probabilities pro…
AREAs-Lab: An Interactive Environment for AI-driven Requirement Elicitation for AI Systems
Pengshan Cai, Zihao Zhang, Ting Jin +8
Building effective AI systems increasingly depends on writing high-quality task requirements, yet users often struggle to articulate the constraints, preferences, and edge cases th…
StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition
Zefang Liu, Chenyang Zhu, Sangwoo Cho +3
Streaming automatic speech recognition (ASR) underperforms on domain-shifted target audio, where labeled in-domain data is costly to prepare while unlabeled audio is abundant. We p…
Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking
Chia-Hsuan Lee, Sihui Dai, Mingyang Zhou +5
Reasoning language models frequently overthink: generating extended chains of behaviors such as hedging, approach abandonment, and self contradiction that consume tokens without im…
SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision
Chia-Hsuan Lee, Zelei Cheng, Yu Wang +4
On-policy distillation (OPD) has a property absent in offline distillation and RL: teacher supervision quality depends on student competence. Incoherent rollouts yield noisy gradie…
Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement
Sangwoo Cho, Kushal Chawla, Pengshan Cai +4
Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, an…
SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation
Chenyang Zhu, Jiayu Yao, Kushal Chawla +10
As autonomous agents tackle increasingly complex multi-step, multi-agent tasks, their execution trajectories have scaled beyond the constraints of even the largest context windows.…
Towards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise Applications
Paresh Dashore, Shreyas Kulkarni, Uttam Gurram +5
Large language model (LLM)-based multi-agent systems demonstrate strong performance on complex reasoning and task execution, enabling broad enterprise applications. However, produc…
T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains
Genta Indra Winata, Amartya Chakraborty, Yuzhen Lin +12
Recent advances in reasoning and tool-calling capabilities of large language models (LLMs) have enabled increasingly capable agentic systems. However, existing benchmarks remain li…
MemGym: a Long-Horizon Memory Environment for LLM Agents
Wujiang Xu, Yu Wang, Kai Mei +8
Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-…
ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models
Zefang Liu, Chenyang Zhu, Sangwoo Cho +1
Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy s…
DIAL-SUMMER: A Structured Evaluation Framework of Hierarchical Errors in Dialogue Summaries
Sahana Ramnath, Nima Chitsazan, Mingyang Zhou +8
Dialogues are a predominant mode of communication for humans, and it is immensely helpful to have automatically generated summaries of them (e.g., to revise key points discussed in…
SPARC-RAG: Adaptive Sequential-Parallel Scaling with Context Management for Retrieval-Augmented Generation
Yuxin Yang, Gangda Deng, Ömer Faruk Akgül +6
Retrieval-Augmented Generation (RAG) grounds large language model outputs in external evidence, but remains challenged on multi-hop question answering that requires long reasoning.…
Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection
Tianyi Niu, Justin Chih-Yao Chen, Genta Indra Winata +6
Large Language Model (LLM) routers dynamically select optimal models for given inputs. Existing approaches typically assume access to ground-truth labeled data, which is often unav…
Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization
Kushal Chawla, Chenyang Zhu, Pengshan Cai +9
Summarization of multi-party dialogues is a critical capability in industry, enhancing knowledge transfer and operational effectiveness across many domains. However, automatically…
Temporal Tokenization Strategies for Event Sequence Modeling with Large Language Models
Zefang Liu, Nam H. Nguyen, Yinzhu Quan +1
Representing continuous time is a critical and under-explored challenge in modeling temporal event sequences with large language models (LLMs). Various strategies like byte-level r…
Leveraging Parameter Space Symmetries for Reasoning Skill Transfer in LLMs
Stefan Horoi, Sangwoo Cho, Supriyo Chakraborty +4
Task arithmetic is a powerful technique for transferring skills between Large Language Models (LLMs), but it often suffers from negative interference when models have diverged duri…
T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
Amartya Chakraborty, Paresh Dashore, Nadia Bathaee +6
Large Language Models (LLMs) have demonstrated impressive capabilities as intelligent agents capable of solving complex problems. However, effective planning in scenarios involving…
Continual Pre-training of MoEs: How robust is your router?
Benjamin Thérien, Charles-Étienne Joseph, Zain Sarwar +7
Sparsely-activated Mixture of Experts (MoE) transformers are promising architectures for foundation models. Compared to dense transformers that require the same amount of floating-…
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
Genta Indra Winata, Frederikus Hudi, Patrick Amadeus Irawan +48
Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate th…
RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization
Hanyang Zhao, Genta Indra Winata, Anirban Das +4
Recently, numerous preference optimization algorithms have been introduced as extensions to the Direct Preference Optimization (DPO) family. While these methods have successfully a…
LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models
Akshaj Kumar Veldanda, Shi-Xiong Zhang, Anirban Das +4
Large language models (LLMs) have revolutionized various domains, yet their utility comes with significant challenges related to outdated or problematic knowledge embedded during p…
Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey
Genta Indra Winata, Hanyang Zhao, Anirban Das +4
Preference tuning is a crucial process for aligning deep generative models with human preferences. This survey offers a thorough overview of recent advancements in preference tunin…