Picture for Hema Swetha Koppula

Hema Swetha Koppula

COMPASS: A Multi-Turn Benchmark for Tool-Mediated Planning & Preference Optimization

Add code
Oct 08, 2025
Viaarxiv icon

Learning to Reason for Hallucination Span Detection

Add code
Oct 02, 2025
Viaarxiv icon

Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization

Add code
Feb 24, 2025
Viaarxiv icon

Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models

Add code
Sep 18, 2023
Viaarxiv icon

Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis

Add code
Mar 27, 2023
Figure 1 for Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis
Figure 2 for Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis
Figure 3 for Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis
Figure 4 for Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis
Viaarxiv icon

Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models

Add code
Oct 06, 2021
Figure 1 for Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
Figure 2 for Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
Figure 3 for Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
Figure 4 for Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
Viaarxiv icon

Learning Human Activities and Object Affordances from RGB-D Videos

Add code
May 06, 2013
Figure 1 for Learning Human Activities and Object Affordances from RGB-D Videos
Figure 2 for Learning Human Activities and Object Affordances from RGB-D Videos
Figure 3 for Learning Human Activities and Object Affordances from RGB-D Videos
Figure 4 for Learning Human Activities and Object Affordances from RGB-D Videos
Viaarxiv icon

Contextually Guided Semantic Labeling and Search for 3D Point Clouds

Add code
Sep 05, 2012
Figure 1 for Contextually Guided Semantic Labeling and Search for 3D Point Clouds
Figure 2 for Contextually Guided Semantic Labeling and Search for 3D Point Clouds
Figure 3 for Contextually Guided Semantic Labeling and Search for 3D Point Clouds
Figure 4 for Contextually Guided Semantic Labeling and Search for 3D Point Clouds
Viaarxiv icon

Human Activity Learning using Object Affordances from RGB-D Videos

Add code
Aug 04, 2012
Figure 1 for Human Activity Learning using Object Affordances from RGB-D Videos
Figure 2 for Human Activity Learning using Object Affordances from RGB-D Videos
Figure 3 for Human Activity Learning using Object Affordances from RGB-D Videos
Figure 4 for Human Activity Learning using Object Affordances from RGB-D Videos
Viaarxiv icon

Labeling 3D scenes for Personal Assistant Robots

Add code
Jun 28, 2011
Figure 1 for Labeling 3D scenes for Personal Assistant Robots
Figure 2 for Labeling 3D scenes for Personal Assistant Robots
Figure 3 for Labeling 3D scenes for Personal Assistant Robots
Figure 4 for Labeling 3D scenes for Personal Assistant Robots
Viaarxiv icon