918博天堂(中国)BIGAI http://www.camnoopy.com Official Homepage for Beijing Institute for General Artificial Intelligence Thu, 27 Nov 2025 08:51:56 +0000 zh-Hans hourly 1 http://wordpress.org/?v=6.8.3 http://www.camnoopy.com/wp-content/uploads/2022/10/cropped-80x80-1-32x32.png 918博天堂(中国)BIGAI http://www.camnoopy.com 32 32 Adaptive Preference Optimization with Uncertainty-aware Utility Anchor http://www.camnoopy.com/blog/2025/11/27/adaptive-preference-optimization-with-uncertainty-aware-utility-anchor/?utm_source=rss&utm_medium=rss&utm_campaign=adaptive-preference-optimization-with-uncertainty-aware-utility-anchor http://www.camnoopy.com/blog/2025/11/27/adaptive-preference-optimization-with-uncertainty-aware-utility-anchor/#respond Thu, 27 Nov 2025 08:51:54 +0000 http://www.camnoopy.com/?p=9280 http://www.camnoopy.com/blog/2025/11/27/adaptive-preference-optimization-with-uncertainty-aware-utility-anchor/feed/ 0 Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks http://www.camnoopy.com/blog/2025/11/27/reinforced-query-reasoners-for-reasoning-intensive-retrieval-tasks/?utm_source=rss&utm_medium=rss&utm_campaign=reinforced-query-reasoners-for-reasoning-intensive-retrieval-tasks http://www.camnoopy.com/blog/2025/11/27/reinforced-query-reasoners-for-reasoning-intensive-retrieval-tasks/#respond Thu, 27 Nov 2025 08:50:43 +0000 http://www.camnoopy.com/?p=9278 http://www.camnoopy.com/blog/2025/11/27/reinforced-query-reasoners-for-reasoning-intensive-retrieval-tasks/feed/ 0 Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs http://www.camnoopy.com/blog/2025/11/27/understanding-and-leveraging-the-expert-specialization-of-context-faithfulness-in-mixture-of-experts-llms/?utm_source=rss&utm_medium=rss&utm_campaign=understanding-and-leveraging-the-expert-specialization-of-context-faithfulness-in-mixture-of-experts-llms http://www.camnoopy.com/blog/2025/11/27/understanding-and-leveraging-the-expert-specialization-of-context-faithfulness-in-mixture-of-experts-llms/#respond Thu, 27 Nov 2025 08:49:37 +0000 http://www.camnoopy.com/?p=9276 http://www.camnoopy.com/blog/2025/11/27/understanding-and-leveraging-the-expert-specialization-of-context-faithfulness-in-mixture-of-experts-llms/feed/ 0 Enhancing LLM-Based Social Bot via an Adversarial Learning Framework http://www.camnoopy.com/blog/2025/11/27/enhancing-llm-based-social-bot-via-an-adversarial-learning-framework/?utm_source=rss&utm_medium=rss&utm_campaign=enhancing-llm-based-social-bot-via-an-adversarial-learning-framework http://www.camnoopy.com/blog/2025/11/27/enhancing-llm-based-social-bot-via-an-adversarial-learning-framework/#respond Thu, 27 Nov 2025 08:48:11 +0000 http://www.camnoopy.com/?p=9274 http://www.camnoopy.com/blog/2025/11/27/enhancing-llm-based-social-bot-via-an-adversarial-learning-framework/feed/ 0 From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes http://www.camnoopy.com/blog/2025/11/27/from-objects-to-anywhere-a-holistic-benchmark-for-multi-level-visual-grounding-in-3d-scenes/?utm_source=rss&utm_medium=rss&utm_campaign=from-objects-to-anywhere-a-holistic-benchmark-for-multi-level-visual-grounding-in-3d-scenes http://www.camnoopy.com/blog/2025/11/27/from-objects-to-anywhere-a-holistic-benchmark-for-multi-level-visual-grounding-in-3d-scenes/#respond Thu, 27 Nov 2025 03:04:38 +0000 http://www.camnoopy.com/?p=9272 http://www.camnoopy.com/blog/2025/11/27/from-objects-to-anywhere-a-holistic-benchmark-for-multi-level-visual-grounding-in-3d-scenes/feed/ 0 Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning http://www.camnoopy.com/blog/2025/11/27/iterative-tool-usage-exploration-for-multimodal-agents-via-step-wise-preference-tuning/?utm_source=rss&utm_medium=rss&utm_campaign=iterative-tool-usage-exploration-for-multimodal-agents-via-step-wise-preference-tuning http://www.camnoopy.com/blog/2025/11/27/iterative-tool-usage-exploration-for-multimodal-agents-via-step-wise-preference-tuning/#respond Thu, 27 Nov 2025 02:59:57 +0000 http://www.camnoopy.com/?p=9270 http://www.camnoopy.com/blog/2025/11/27/iterative-tool-usage-exploration-for-multimodal-agents-via-step-wise-preference-tuning/feed/ 0