Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks209 from public data
- LIMO: Less is More for Reasoning546
It is demonstrated that sophisticated mathematical reasoning can emerge with only a few examples and suggested that the threshold for eliciting complex reasoning is not dictated by task complexity but rather by two key factors: the completeness of the model's pre-trained knowledge base and the effectiveness of post-training examples in serving as cognitive templates that guide reasoning.
- Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification230
This work proposes a span-based extract-then-classify framework, where multiple opinion targets are directly extracted from the sentence under the supervision of target span boundaries, and corresponding polarities are then classified using their span representations.
- Reinforced Mnemonic Reader for Machine Reading Comprehension216
The Reinforced Mnemonic Reader for machine reading comprehension tasks, which enhances previous attentive readers in two aspects: a reattention mechanism is proposed to refine current attentions by directly accessing to past attentions that are temporally memorized in a multi-round alignment architecture.
- Read + Verify: Machine Reading Comprehension with Unanswerable Questions164
This work proposes a novel read-then-verify system, which not only utilizes a neural reader to extract candidate answers and produce no-answer probabilities, but also leverages an answer verifier to decide whether the predicted answer is entailed by the input snippets.
- A social network approach to trust management in VANETs131
To the best of the knowledge, this work is the first to introduce information cascading and oversampling to VANETs, and shows that simple voting for decision making leads to oversamplings and gives incorrect results in VANets.
- A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning99
The Multi-Type Multi-Span Network (MTMSN) is introduced, a neural reading comprehension model that combines a multi-type answer predictor designed to support various answer types with amulti-span extraction method for dynamically producing one or multiple text spans.
- From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning78
This work proposes a novel supervised pinpoint tuning (SPT), where the region-of-interest modules are tuned for a given objective, and demonstrates that SPT significantly mitigates the sycophancy issue of LLMs (even better than SFT).
- Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition78
This work designs a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
- Attention-Guided Answer Distillation for Machine Reading Comprehension77
This paper demonstrates that vanilla knowledge distillation applied to answer span prediction is effective for reading comprehension systems and proposes two novel approaches that not only penalize the prediction on confusing answers but also guide the training with alignment information distilled from the ensemble.
- Alterations of Muscle Synergies During Voluntary Arm Reaching Movement in Subacute Stroke Survivors at Different Levels of Impairment72
By comparing the structure of muscle synergies and the similarity of activation coefficients across groups, this paper can validate the increasing activation of pectoralis major muscle and the decreasing activation of elbow extensor of triceps in stroke groups.
- Learning Environmental Sounds with Multi-scale Convolutional Neural Network72
A novel end-to-end network called WaveMsNet is proposed based on the multi-scale convolution operation and two-phase method, which can get better audio representation by improving the frequency resolution and learning filters cross all frequency area.
- Rapid adaptation for deep neural networks through multi-task learning70
The proposed MTL adaptation framework improves the learning ability of the original DNN structure, then enlarge the coverage of the acoustic space to deal with the unseen senone problem, and thus enhance the discrimination power of the adapted DNN models.
- Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension69
RE^3QA is presented, a unified question answering model that combines context retrieving, reading comprehension, and answer reranking to predict the final answer and outperforms the pipelined baseline and achieves state-of-the-art results on two versions of TriviaQA and two variants of SQuAD.
- Recent Trends in Deep Learning Based Open-Domain Textual Question Answering Systems67
This work presents a thorough survey to explicitly give the task scope of open-domain textual QA, overview recent key advancements on deep learning based open- domain textualQA, illustrate the models and acceleration methods in detail, and introduce open- domains textual QC datasets and evaluation metrics.
- DNN-based speech bandwidth expansion and its application to adding high-frequency missing features for automatic speech recognition of narrowband speech65
These techniques not only improve over the traditionally-adopted objective and subjective measures but also reduce the word error rate (WER) from 8.67% when recognizing narrowband speech to 8.26% when recognizing bandwidth-expanded speech.
- Automating psychological hypothesis generation with AI: when large language models meet causal graph63
The results show that combining LLM with machine learning techniques such as causal knowledge graphs can revolutionize automated discovery in psychology, extracting novel insights from the extensive literature.
- 56
- Motor Function Assessment of Upper Limb in Stroke Patients52
The five features proposed in this paper can quantitatively evaluate the motor function of stroke patients which is very useful in the rehabilitation process.
- 52
- 50
- 48
- Electroacupuncture as an adjunctive therapy for motor dysfunction in acute stroke survivors: a systematic review and meta-analyses48
This review provides new evidence for the effectiveness and safety of EA combined with RT and/or CD for PSMD, however, the results should be interpreted cautiously because of methodological weakness and publication bias.
- Exploring Fourier Prior for Single Image Rain Removal47
A two-stage model where the first stage restoring the amplitude of rainy images to clean rain streaks, and the second stage restores the phase information to refine fine-grained background structures to improve the generalization ability of an image rain removal model.
- SNDCNN: Self-Normalizing Deep CNNs with Scaled Exponential Linear Units for Speech Recognition42
The self-normalizing deep CNN (SNDCNN) based acoustic model topology is proposed, by removing the SC/BN and replacing the typical RELU activations with scaled exponential linear unit (SELU) in ResNet-50.
- 41
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 2026-10-15. 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.