AI研究論文每日精選

每日精選AI研究論文及翻譯

VITA：邁向開源互動式全方位多模態LLM
VITA: Towards Open-Source Interactive Omni Multimodal LLM

Chaoyou Fu, Haojia Lin, Zuwei Long, Yunhang Shen, Meng Zhao, Yifan Zhang, Xiong Wang, Di Yin, Long Ma, Xiawu Zheng, Ran He, Rongrong Ji, Yunsheng Wu, Caifeng Shan, Xing Sun•Aug 9, 2024•493

Gemma 範圍：在 Gemma 2 上一次性地開啟處處存在的開放稀疏自編碼器
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Nicolas Sonnerat, Vikrant Varma, János Kramár, Anca Dragan, Rohin Shah, Neel Nanda•Aug 9, 2024•402

mPLUG-Owl3：朝向多模式大型語言模型中的長圖像序列理解
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

Jiabo Ye, Haiyang Xu, Haowei Liu, Anwen Hu, Ming Yan, Qi Qian, Ji Zhang, Fei Huang, Jingren Zhou•Aug 9, 2024•352

UniBench：視覺推理需要重新思考視覺語言超越規模化
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

Haider Al-Tahan, Quentin Garrido, Randall Balestriero, Diane Bouchacourt, Caner Hazirbas, Mark Ibrahim•Aug 9, 2024•252

ToolSandbox：一個具有狀態、對話式、互動式的評估基準，用於評估LLM工具的使用能力。
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Jiarui Lu, Thomas Holleis, Yizhe Zhang, Bernhard Aumayer, Feng Nan, Felix Bai, Shuang Ma, Shen Ma, Mengyu Li, Guoli Yin, Zirui Wang, Ruoming Pang•Aug 8, 2024•184

從語言模型生成新穎的實驗性假設：跨及物動詞的一個案例研究
Generating novel experimental hypotheses from language models: A case study on cross-dative generalization

Kanishka Misra, Najoung Kim•Aug 9, 2024•61

AI研究論文每日精選

VITA：邁向開源互動式全方位多模態LLM
VITA: Towards Open-Source Interactive Omni Multimodal LLM

Gemma 範圍：在 Gemma 2 上一次性地開啟處處存在的開放稀疏自編碼器
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

mPLUG-Owl3：朝向多模式大型語言模型中的長圖像序列理解
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

UniBench：視覺推理需要重新思考視覺語言超越規模化
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

ToolSandbox：一個具有狀態、對話式、互動式的評估基準，用於評估LLM工具的使用能力。
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Kalman啟發的特徵傳播用於視頻人臉超分辨率
Kalman-Inspired Feature Propagation for Video Face Super-Resolution

BRAT：用於架構無關文本反轉的獎勵正交標記
BRAT: Bonus oRthogonAl Token for Architecture Agnostic Textual Inversion

MooER：基於LLM的語音識別和翻譯模型，來自Moore Threads
MooER: LLM-based Speech Recognition and Translation Models from Moore Threads

MulliVC：具有循環一致性的多語言語音轉換
MulliVC: Multi-lingual Voice Conversion With Cycle Consistency

從語言模型生成新穎的實驗性假設：跨及物動詞的一個案例研究
Generating novel experimental hypotheses from language models: A case study on cross-dative generalization

Support

AI研究論文每日精選

VITA：邁向開源互動式全方位多模態LLM
VITA: Towards Open-Source Interactive Omni Multimodal LLM

Gemma 範圍：在 Gemma 2 上一次性地開啟處處存在的開放稀疏自編碼器
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

mPLUG-Owl3：朝向多模式大型語言模型中的長圖像序列理解
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

UniBench：視覺推理需要重新思考視覺語言超越規模化
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

ToolSandbox：一個具有狀態、對話式、互動式的評估基準，用於評估LLM工具的使用能力。
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Kalman啟發的特徵傳播用於視頻人臉超分辨率
Kalman-Inspired Feature Propagation for Video Face Super-Resolution

BRAT：用於架構無關文本反轉的獎勵正交標記
BRAT: Bonus oRthogonAl Token for Architecture Agnostic Textual Inversion

MooER：基於LLM的語音識別和翻譯模型，來自Moore Threads
MooER: LLM-based Speech Recognition and Translation Models from Moore Threads

MulliVC：具有循環一致性的多語言語音轉換
MulliVC: Multi-lingual Voice Conversion With Cycle Consistency

從語言模型生成新穎的實驗性假設：跨及物動詞的一個案例研究
Generating novel experimental hypotheses from language models: A case study on cross-dative generalization