新闻
Search and Refine During Think: Autonomous Retrieval-Augmented Reasoning of LLMs
arXiv:2505.11277v3 Announce Type: replace Abstract: Large language models have demonstrated impressive reasoning capabilities but are...
SEA-LION: Southeast Asian Languages in One Network
arXiv:2504.05747v3 Announce Type: replace Abstract: Recently, Large Language Models (LLMs) have dominated much of the...
SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models
arXiv:2508.15648v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at various natural language processing...
Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning
arXiv:2502.13820v3 Announce Type: replace-cross Abstract: Synthetic verification techniques such as generating test cases and reward...
SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines
arXiv:2509.21320v3 Announce Type: replace Abstract: We present a scientific reasoning foundation model that aligns natural...
Scientists’ First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning
arXiv:2506.10521v2 Announce Type: replace-cross Abstract: Scientific discoveries increasingly rely on complex multimodal reasoning based on...
Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
arXiv:2504.02438v5 Announce Type: replace Abstract: Long-form video processing fundamentally challenges vision-language models (VLMs) due to...
Scaling Truth: The Confidence Paradox in AI Fact-Checking
arXiv:2509.08803v1 Announce Type: cross Abstract: The rise of misinformation underscores the need for scalable and...
Scaling Multimodal Search and Recommendation with Small Language Models via Upside-Down Reinforcement Learning
arXiv:2502.09854v2 Announce Type: replace Abstract: In this work, we investigate how small language models (SLMs)...
Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
arXiv:2505.13227v2 Announce Type: replace-cross Abstract: Graphical user interface (GUI) grounding, the ability to map natural...
ScaleFormer: Span Representation Cumulation for Long-Context Transformer
arXiv:2511.10029v1 Announce Type: new Abstract: The quadratic complexity of standard self-attention severely limits the application...
ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
arXiv:2506.19848v1 Announce Type: cross Abstract: This paper presents ScaleCap, an inference-time scalable image captioning strategy...
