Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks45 from public data
- From System 1 to System 2: A Survey of Reasoning Large Language Models314
This survey provides an overview of the progress in foundational LLMs and the early development of System 2 technologies, exploring how their combination has paved the way for reasoning LLMs and explores promising directions for advancing reasoning LLMs.
- 130
- DualGATs: Dual Graph Attention Networks for Emotion Recognition in Conversations100
This paper introduces Dual Graph ATtention networks (DualGATs) to concurrently consider the complementary aspects of discourse structure and speaker-aware context, aiming for more precise ERC.
- Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents80
This work proposes AutoTools, a framework that enables LLMs to automate the tool-use workflow, and proposes the AutoTools-Learning approach, training the LLMs with three learning tasks on 34k instances of high-quality synthetic data, including documentation understanding, relevance learning, and function programming.
- Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation77
A prior selection module is enhanced with the necessary posterior information obtained from the specially designed Posterior Information Prediction Module (PIPM) and a Knowledge Distillation Based Training Strategy (KDBTS) is proposed to train the decoder with the knowledge selected from the prior distribution, removing the exposure bias of knowledge selection.
- Knowledge Aware Emotion Recognition in Textual Conversations via Multi-Task Incremental Transformer53
This paper proposes a novel Knowledge Aware Incremental Transformer with Multi-task Learning (KAITML) and is the first to introduce multi-task learning to alleviate the aforementioned confusion and thus further improve the emotion recognition performance.
- A Working Memory Model for Task-oriented Dialog Response Generation43
A working memory model (WMM2Seq) for dialog response generation that adopts a working memory to interact with two separated long-term memories, which are the episodic memory for memorizing dialog history and the semantic memory for storing KB tuples.
- GoG: Relation-aware Graph-over-Graph Network for Visual Dialog38
A novel relation-aware graph-over-graph network (GoG) for visual dialog that outperforms the strong baseline in both generative and discriminative settings by a significant margin.
- 31
- TSAM: A Two-Stream Attention Model for Causal Emotion Entailment29
A Two-Stream Attention Model (TSAM) is proposed to effectively model the speaker’s emotional influences in the conversational history and achieves new State-Of-The-Art (SOTA) performance and outperforms baselines remarkably.
- Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation27
A multi-turn dialogue history combined with visual scene step by step according to the order of the dialogue and then generates a contextually and visually coherent response, named MITVG, which achieves comparable performance on the VisDial datasets.
- Modeling Attention and Memory for Auditory Selection in a Cocktail Party Environment26
A unified Auditory Selection framework with Attention and Memory (dubbed ASAM) is proposed, which accumulates the prior knowledge into a life-long memory during the training phase, meanwhile a speech perceptor is trained to extract the temporal acoustic feature and update the memory online when a salient speech is given.
- Task Relation Distillation and Prototypical Pseudo Label for Incremental Named Entity Recognition22
To tackle catastrophic forgetting, a task relation distillation scheme is introduced that serves two purposes: ensuring inter-task semantic consistency across different incremental learning tasks by minimizing inter- task relation Distillation loss, and enhancing the model's prediction confidence by minimizing intra-task self-entropy loss.
- 22
- Decomposing Logits Distillation for Incremental Named Entity Recognition20
It is discovered that a predicted logit can be decomposed into two terms that measure the likelihood of an input token belonging to a specific entity type or not, and a novel Decomposing Logits Distillation (DLD) method is proposed, enhancing the model's ability to retain old knowledge and mitigate catastrophic forgetting.
- 20
- 19
- Unsupervised and Pseudo-Supervised Vision-Language Alignment in Visual Dialog18
The proposed AlignVD achieves new state-of-the-art results on the visual dialog challenge leaderboard with a NDCG metric of 78.70, surpassing the previous best ensemble model by about 1 point.
- Learning to Ground Visual Objects for Visual Dialog18
This paper proposes a novel approach to Learn to Ground visual objects for visual dialog, which employs a novel visual objects grounding mechanism where both prior and posterior distributions over visual objects are used to facilitate visual objects grounded.
- Unsupervised Knowledge Selection for Dialogue Generation17
A novel Distilled Distant Supervision Loss (DDSL) is proposed to supervise knowledge selection when the gold knowledge label is unknown and manages to select knowledge more accurately in the unsupervised setting and generates more informative responses, even outperforming many strong supervised baselines.
- 16
- Lifelong Text-Audio Sentiment Analysis learning16
A novel Lifelong Text-Audio Sentiment Analysis (LTASA) model is proposed to continuously learn text-audio sentiment analysis tasks, which effectively explores intrinsic semantic relationships from both intra- modality and inter-modality perspectives.
- 15
- 15
- 14
- 13
- Flexible Weight Tuning and Weight Fusion Strategies for Continual Named Entity Recognition10
Flexible Weight Tuning and Weight Fusion strategies for CNER are introduced that seamlessly integrate with existing State-Of-The-Art (SOTA) models and consistently enhance the performance of previous SOTA meth-ods across ten CNER settings in three datasets.
- Matching-Based Term Semantics Pre-Training for Spoken Patient Query Understanding8
A Term Semantics Pre-trained Matching Network (TSPMN) that takes both terms and queries as input to model their semantic inter-action and further design two self-supervised objectives, including Contrastive Term Discrimination and Matching-based Mask Term Modeling.
- HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval8
A novel hierarchical retrieval objective is designed, which uses the representation of different dimensions for coarse-to-fine ITR, i.e., using low-dimensional representation for large-scale coarse retrieval and high- dimensional representation for small-scale fine retrieval.
- 6
- 5
- Crucial Semantic Classifier-based Adversarial Learning for Unsupervised Domain Adaptation4
This work proposes Crucial Semantic Classifier-based Adversarial Learning (CSCAL), which pays more attention to crucial semantic knowledge transferring and leverages the classifier to implicitly play the role of domain discriminator without extra network designing and effectively mitigates distribution shifts between the source and target domains from both intra- and inter-class perspectives.
- 3
- MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models2
This work introduces MathReal, a meticulously curated dataset comprising 2,000 mathematical questions with images captured by handheld mobile devices in authentic scenarios, and designs six experimental settings that enable a systematic analysis of their performance and error patterns.
- 1
- 1
- 1
- 1
- –
- Type-Balanced Contextual Learning for Incremental Named Entity Recognition–
This analysis shows that, in new sentences, the contextual associations of tokens representing old entity types exhibit a significantly stronger bias towards new entity types compared to their contexts in old sentences, which intensifies the degradation of old knowledge while promoting the overfitting of new knowledge.
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.