Search Results for author:
Found 24 papers, 17 papers with code
Supervised Optimism Correction: Be Confident When LLMs Are Sure
In this work, we establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning under the token-level Markov decision process, revealing that large language models indeed learn an implicit $Q$-function for inference.
OpenOmni: Large Language Models Pivot Zero-shot Omnimodal Alignment across Language with Real-time Self-Aware Emotional Speech Synthesis
In the alignment phase, a pre-trained speech model is further trained on text-image tasks to generalize from vision to speech in a (near) zero-shot manner, outperforming models trained on tri-modal datasets.
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct
This framework iteratively improve data quality through a refined combination of fine-grained perception, cognitive reasoning, and interaction evolution, generating a more complex and diverse image-text instruction dataset that empowers MLLMs with enhanced capabilities.
DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception
The development of large language models (LLMs) has significantly advanced the emergence of large multimodal models (LMMs).
A Survey on Self-Evolution of Large Language Models
To address this issue, self-evolution approaches that enable LLM to autonomously acquire, refine, and learn from experiences generated by the model itself are rapidly growing.
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
Furthermore, it is complementary to existing methods.
Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use
Specifically, the crucial information in the context will be potentially overlooked by model when it is positioned in the trough zone of the attention waveform, leading to decreased performance.
Ranked #2 on
Trajectory Planning
on ToolBench
Improving Factual Consistency of Text Summarization by Adversarially Decoupling Comprehension and Embellishment Abilities of LLMs
Despite the recent progress in text summarization made by large language models (LLMs), they often generate summaries that are factually inconsistent with original articles, known as "hallucinations" in text generation.
Constructive Large Language Models Alignment with Diverse Feedback
This limitation leads to suboptimal performance, even when ample training data is available.
Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models
Task-oriented dialogue (TOD) systems facilitate users in executing various activities via multi-turn dialogues, but Large Language Models (LLMs) often struggle to comprehend these intricate contexts.
UniSA: Unified Generative Framework for Sentiment Analysis
Sentiment analysis is a crucial task that aims to understand people's emotional states and predict emotional categories based on multimodal information.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents
SpokenWOZ further incorporates common spoken characteristics such as word-by-word processing and reasoning in spoken language.
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
In this paper, we propose Speech-text dialog Pre-training for spoken dialog understanding with ExpliCiT cRoss-Modal Alignment (SPECTRA), which is the first-ever speech-text dialog pre-training model.
Ranked #2 on
Multimodal Sentiment Analysis
on CMU-MOSI
(Acc-2 metric, using extra
training data)
cross-modal alignment
Emotion Recognition in Conversation
+2
Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation
Dialogue Topic Segmentation (DTS) plays an essential role in a variety of dialogue modeling tasks.
Empathetic Response Generation via Emotion Cause Transition Graph
Empathetic dialogue is a human-like behavior that requires the perception of both affective factors (e. g., emotion status) and cognitive factors (e. g., cause of the emotion).
Multi-View Active Fine-Grained Visual Recognition
Despite the remarkable progress of Fine-grained visual classification (FGVC) with years of history, it is still limited to recognizing 2 images.
Fine-Grained Image Classification
Fine-Grained Visual Recognition
UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition
Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors.
Ranked #3 on
Multimodal Sentiment Analysis
on CMU-MOSI
Multi-View Active Fine-Grained Recognition
As fine-grained visual classification (FGVC) being developed for decades, great works related have exposed a key direction -- finding discriminative local regions and revealing subtle differences.
Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems
In this paper, we present Duplex Conversation, a multi-turn, multimodal spoken dialogue system that enables telephone-based agents to interact with customers like a human.
Deep Open Intent Classification with Adaptive Decision Boundary
In this paper, we propose a post-processing method to learn the adaptive decision boundary (ADB) for open intent classification.
Ranked #1 on
Open Intent Detection
on StackOverFlow(75%known)
Discovering New Intents with Deep Aligned Clustering
In this work, we propose an effective method, Deep Aligned Clustering, to discover new intents with the aid of the limited known intent data.
Ranked #2 on
Open Intent Discovery
on CLINC150
A Post-processing Method for Detecting Unknown Intent of Dialogue System via Pre-trained Deep Neural Network Classifier
In this paper, we propose SofterMax and deep novelty detection (SMDN), a simple yet effective post-processing method for detecting unknown intent in dialogue systems based on pre-trained deep neural network classifiers.
Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement
Identifying new user intents is an essential task in the dialogue system.
Ranked #1 on
Open Intent Discovery
on ATIS
Deep Unknown Intent Detection with Margin Loss
With margin loss, we can learn discriminative deep features by forcing the network to maximize inter-class variance and to minimize intra-class variance.
Ranked #1 on
Open Intent Detection
on SNIPS (25% known)
