Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks12 from public data
- MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation94
The introduction of MMLU-ProX, a comprehensive benchmark covering 29 languages, built on an English benchmark, and systematically evaluate 36 state-of-the-art LLMs, including reasoning-enhanced and multilingual-optimized LLMs reveal significant disparities in the multilingual capabilities of LLMs.
- Deep Semantic Dictionary Learning for Multi-label Image Classification92
A novel end-to-end model named Deep Semantic Dictionary Learning (DSDL) is designed and a novel training strategy named Alternately Parameters Update Strategy (APUS) is devised for optimizing DSDL, which alternately optimizes the representation coefficients and the semantic dictionary in forward and backward propagation.
- 78
- CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model51
CAT-SAM is presented, a ConditionAl Tuning network that adapts SAM toward various unconventional target tasks with just few-shot target samples, and two CAT-SAM variants achieve superior target segmentation performance consistently even under the very challenging one-shot adaptation setup.
- 23
- 19
- MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models18
This paper reveals the negative impact of the long-term decay in Rotary Position Encoding (RoPE), used for positional modeling in LVLMs, and proposes MCA-LLaVA, which extends the long-term decay to a two-dimensional, multi-directional spatial decay, mitigating hallucinations by alleviating image alignment bias.
- 18
- 16
- 11
- Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation5
Concept Curation (CoCu), a pipeline that leverages CLIP to compensate for the missing semantics of visual concepts captured in textual representations, is proposed, suggesting the value of bridging semantic gap in pre-training data.
- Face Recognition Based on Gabor Enhanced Marginal Fisher Model and Error Correction SVM3
The GEMFM method has better generalization ability for testing data, and therefore is more capable for the task of feature extraction in face recognition, and is integrated with the error correction SVM classifier to form a new face recognition system.
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. 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. You will be asked to sign in.