5 papers
YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition
PSBC LLM Team, Huawei LLM Team, Ruihan Long +56
Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates inf…
On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective
Yikai Guo, Bin Wang, Xilai Fan +2
AI-generated text increasingly blends with human writing, raising practical risks such as misinformation, academic misuse, and corpora contamination. While statistical detectors ar…
FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
Chunyu Xie, Bin Wang, Fanjing Kong +5
Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, parti…
FG-CLIP: Fine-Grained Visual and Textual Alignment
Chunyu Xie, Bin Wang, Fanjing Kong +5
Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding du…
IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities
Bin Wang, Chunyu Xie, Dawei Leng +1
In the field of multimodal large language models (MLLMs), common methods typically involve unfreezing the language model during training to foster profound visual understanding. Ho…