Search Results for author:
Found 20 papers, 9 papers with code
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
Large language models (LLMs) have shown remarkable advancements in enabling language agents to tackle simple tasks.
Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities
Spoken dialogue modeling introduces unique challenges beyond text-based language modeling, demanding robust turn-taking, backchanneling, and real-time interaction.
Audio Texture Manipulation by Exemplar-Based Analogy
Audio texture manipulation involves modifying the perceptual characteristics of a sound to achieve specific transformations, such as adding, removing, or replacing auditory elements.
PokerBench: Training Large Language Models to become Professional Poker Players
PokerBench thus presents a unique benchmark for a quick and reliable evaluation of the poker-playing ability of LLMs as well as a comprehensive benchmark to study the progress of LLMs in complex game-playing scenarios.
FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression
We compare traditional text compression systems with neural network and LLM-based text compression methods.
Self-Supervised Audio-Visual Soundscape Stylization
Through this process, the model learns to transfer the conditional example's sound properties to the input speech.
Time and Tokens: Benchmarking End-to-End Speech Dysfluency Detection
In this work, we revisit this problem from a new perspective: tokenizing dysfluencies and modeling the detection problem as a token-based automatic speech recognition (ASR) problem.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Geometric Interpretation of Layer Normalization and a Comparative Analysis with RMSNorm
Finally, we compare the hidden representations of LayerNorm-based LLMs with models trained using RMSNorm and show that all LLMs naturally operate orthogonal to the uniform vector at inference time, that is, on average they do not have a component along the uniform vector during inference.
Stutter-Solver: End-to-end Multi-lingual Dysfluency Detection
Current de-facto dysfluency modeling methods utilize template matching algorithms which are not generalizable to out-of-domain real-world dysfluencies across languages, and are not scalable with increasing amounts of training data.
TinyAgent: Function Calling at the Edge
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 calling.
Multimodal Segmentation for Vocal Tract Modeling
Together, we set a new benchmark for vocal tract modeling in MRI video segmentation and use this to release labels for a 75-speaker RT-MRI dataset, increasing the amount of labeled public RT-MRI data of the vocal tract by over a factor of 9.
Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3
This study presents a targeted model editing analysis focused on the latest large language model, Llama-3.
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
To address this, we propose LLM2LLM, a targeted and iterative data augmentation strategy that uses a teacher LLM to enhance a small seed dataset by augmenting additional data that can be used for fine-tuning on a specific task.
A Unified Framework for Model Editing
We generalize ROME and enable batched editing with equality constraint in the form of EMMET - an Equality-constrained Mass Model Editing algorithm for Transformers, a new batched memory-editing algorithm.
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
With this paper, we provide a more stable implementation ROME, which we call r-ROME and show that model collapse is no longer observed when making large scale sequential edits with r-ROME, while further improving generalization and locality of model editing compared to the original implementation of ROME.
Identifying Multiple Personalities in Large Language Models with External Evaluation
In this paper, we investigate LLM personalities using an alternate personality measurement method, which we refer to as the external evaluation method, where instead of prompting LLMs with multiple-choice questions in the Likert scale, we evaluate LLMs' personalities by analyzing their responses toward open-ended situational questions using an external machine learning model.
Towards Hierarchical Spoken Language Dysfluency Modeling
Speech disfluency modeling is the bottleneck for both speech therapy and language learning.
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
With this in mind, we evaluate the current model editing methods at scale, focusing on two state of the art methods: ROME and MEMIT.
Towards an Interpretable Representation of Speaker Identity via Perceptual Voice Qualities
Unlike other data modalities such as text and vision, speech does not lend itself to easy interpretation.
Self-Assessment Tests are Unreliable Measures of LLM Personality
These simple tests, done on ChatGPT and three Llama2 models of different sizes, show that self-assessment personality tests created for humans are unreliable measures of personality in LLMs.
