Soujanya Poria

Multimodal Sarcasm Detection Dataset

Attention-based multimodal fusion for sentiment analysis

No description provided.

NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

Contextual inter modal attention for multimodal sentiment analysis

This repository contains the official implementation of Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision.

NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks

Aspect extraction from product reviews - window-CNN+maxpool+CRF, BiLSTM+CRF, MLP+CRF

TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

Codes and datasets for the paper Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique

Test LLMs against jailbreaks and unprecedented harms

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling

No description provided.

This repository is maintained to release dataset and models for multimodal puzzle reasoning.

Restore safety in fine-tuned language models through task arithmetic

Mustango: Toward Controllable Text-to-Music Generation

Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Codes and Model of the paper "Text-to-Audio Generation using Instruction Tuned LLM and Latent Diffusion Model"

This repository contains code for extending the Stanford Alpaca synthetic instruction tuning to existing instruction-tuned models such as Flan-T5.

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

Context-Dependent Sentiment Analysis in User-Generated Videos

Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient transfer learning approaches on SURE benchmark for speech understanding

This repository implements our EMNLP 2022 research paper A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach.

No description provided.

NAACL 2022 paper on Analyzing Modality Robustness in Multimodal Sentiment Analysis

No description provided.