16 citations · 60 across the 78 of their papers we have counts for
26 papers · 1 filter
KIRA: A Full-Stack Reading Screening System with Dual-Pathway Analysis for Children
Maggie Dong, Rohit Mekkoth, Zixuan Wang +3
Early-grade reading screening is critical for identifying children at risk of reading difficulty. Existing AI-based screeners are often limited in the scope of their analyses and e…
Automated Discovery Has No Universally Superior Harness
Akshat Gupta, Jermaine Lei, Alexander Lu +2
Autonomous discovery systems such as OpenEvolve and TTT-Discover are often used as general-purpose harnesses. However, in practice these are composite systems combining several des…
S-MARC: Causal Streaming Reasoning for Full-Duplex Conversational Behavior Modeling
Dingkun Zhou, Shuchang Pan, Jiachen Lian +11
Human conversation is organized by an implicit chain of thought and manifests as temporally structured conversational behaviors. Capturing this perceptual pathway is critical for b…
Enabling Conversational Behavior Reasoning Capabilities in Full-Duplex Speech
Shuchang Pan, Siddharth Banerjee, Dhruv Hebbar +9
Human conversation is organized by an implicit chain of thoughts that manifests as timed speech acts. Capturing this causal pathway is key to building natural full-duplex interacti…
How Do LLMs Use Their Depth?
Akshat Gupta, Jay Yeung, Gopala Anumanchipalli +1
Growing evidence suggests that large language models do not use their depth uniformly, yet we still lack a fine-grained understanding of their layer-wise prediction dynamics. In th…
The Oracle Has Spoken: A Multi-Aspect Evaluation of Dialogue in Pythia
Zixun Chen, Petr Babkin, Akshat Gupta +2
Dialogue is one of the landmark abilities of large language models (LLMs). Despite its ubiquity, few studies actually distinguish specific ingredients underpinning dialogue behavio…
Scaling Spoken Language Models with Syllabic Speech Tokenization
Nicholas Lee, Cheol Jun Cho, Alan W Black +1
Spoken language models (SLMs) typically discretize speech into high-frame-rate tokens extracted from SSL speech models. As the most successful LMs are based on the Transformer arch…
EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Spoken Dialogue Systems
Jingwen Liu, Kan Jen Cheng, Jiachen Lian +8
Speech emotions play a crucial role in human-computer interaction, shaping engagement and context-aware communication. Despite recent advances in spoken dialogue systems, a holisti…
K-Function: Joint Pronunciation Transcription and Feedback for Evaluating Kids Language Function
Shuhe Li, Chenxu Guo, Jiachen Lian +18
Evaluating young children's language is challenging for automatic speech recognizers due to high-pitched voices, prolonged sounds, and limited data. We introduce K-Function, a fram…
Efficient Knowledge Editing via Minimal Precomputation
Akshat Gupta, Maochuan Lu, Thomas Hartvigsen +1
Knowledge editing methods like MEMIT are able to make data and compute efficient updates of factual knowledge by using a single sentence to update facts and their consequences. How…
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
Lutfi Eren Erdogan, Nicholas Lee, Sehoon Kim +5
Large language models (LLMs) have shown remarkable advancements in enabling language agents to tackle simple tasks. However, applying them for complex, multi-step, long-horizon tas…
Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities
Guan-Ting Lin, Jiachen Lian, Tingle Li +4
Spoken dialogue modeling poses challenges beyond text-based language modeling, requiring real-time interaction, turn-taking, and backchanneling. While most Spoken Dialogue Models (…
Norm Growth and Stability Challenges in Localized Sequential Knowledge Editing
Akshat Gupta, Christine Fang, Atahan Ozdemir +4
This study investigates the impact of localized updates to large language models (LLMs), specifically in the context of knowledge editing - a task aimed at incorporating or modifyi…
Lifelong Knowledge Editing requires Better Regularization
Akshat Gupta, Phudish Prateepamornkul, Maochuan Lu +3
Knowledge editing is a promising way to improve factuality in large language models, but recent studies have shown significant model degradation during sequential editing. In this…
PokerBench: Training Large Language Models to become Professional Poker Players
Richard Zhuang, Akshat Gupta, Richard Yang +3
We introduce PokerBench - a benchmark for evaluating the poker-playing abilities of large language models (LLMs). As LLMs excel in traditional NLP tasks, their application to compl…
TinyAgent: Function Calling at the Edge
Lutfi Eren Erdogan, Nicholas Lee, Siddharth Jha +7
Recent large language models (LLMs) have enabled the development of advanced agentic systems that can integrate various tools and APIs to fulfill user queries through function call…
Sylber: Syllabic Embedding Representation of Speech from Raw Audio
Cheol Jun Cho, Nicholas Lee, Akshat Gupta +4
Syllables are compositional units of spoken language that efficiently structure human speech perception and production. However, current neural speech representations lack such str…
FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression
Fazal Mittu, Yihuan Bu, Akshat Gupta +4
While the language modeling objective has been shown to be deeply connected with compression, it is surprising that modern LLMs are not employed in practical text compression syste…
Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3
Junsang Yoon, Akshat Gupta, Gopala Anumanchipalli
This study presents a targeted model editing analysis focused on the latest large language model, Llama-3. We explore the efficacy of popular model editing techniques - ROME, MEMIT…
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
Nicholas Lee, Thanakul Wattanawong, Sehoon Kim +6
Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still…
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
Akshat Gupta, Sidharth Baskaran, Gopala Anumanchipalli
Recent work using Rank-One Model Editing (ROME), a popular model editing method, has shown that there are certain facts that the algorithm is unable to edit without breaking the mo…
Identifying Multiple Personalities in Large Language Models with External Evaluation
Xiaoyang Song, Yuta Adachi, Jessie Feng +6
As Large Language Models (LLMs) are integrated with human daily applications rapidly, many societal and ethical concerns are raised regarding the behavior of LLMs. One of the ways…
Towards Hierarchical Spoken Language Dysfluency Modeling
Jiachen Lian, Gopala Anumanchipalli
Speech disfluency modeling is the bottleneck for both speech therapy and language learning. However, there is no effective AI solution to systematically tackle this problem. We sol…
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
Akshat Gupta, Anurag Rao, Gopala Anumanchipalli
Editing knowledge in large language models is an attractive capability to have which allows us to correct incorrectly learnt facts during pre-training, as well as update the model…