Alignment faking in large language models
21:35
Alignment faking in large language models
5 сағат бұрын
RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation
24:09
RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation
7 сағат бұрын
ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
16:28
ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
10 сағат бұрын
RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation
19:26
RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation
12 сағат бұрын
ChatQA: Surpassing GPT-4 on Conversational QA and RAG
42:03
ChatQA: Surpassing GPT-4 on Conversational QA and RAG
14 сағат бұрын
Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions
14:26
Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions
17 сағат бұрын
Phi 4 Technical Report
45:16
Phi 4 Technical Report
19 сағат бұрын
The BrowserGym Ecosystem for Web Agent Research
40:44
The BrowserGym Ecosystem for Web Agent Research
22 сағат бұрын
Sora System Card
22:10
Sora System Card
Күн бұрын
Densing Law of LLMs
18:17
Densing Law of LLMs
Күн бұрын
ProcessBench: Identifying Process Errors in Mathematical Reasoning
10:06
ProcessBench: Identifying Process Errors in Mathematical Reasoning
Күн бұрын
100% Hallucination Elimination Using Acurai
16:59
100% Hallucination Elimination Using Acurai
Күн бұрын
OpenAI o1 System Card
27:29
OpenAI o1 System Card
Күн бұрын
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
12:43
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
14 күн бұрын
Zero-Indexing Internet Search Augmented Generation for Large Language Models
22:46
Zero-Indexing Internet Search Augmented Generation for Large Language Models
14 күн бұрын
Open-Sora Plan: Open-Source Large Video Generation Model
22:54
Open-Sora Plan: Open-Source Large Video Generation Model
14 күн бұрын
Scaling Transformers for Low-Bitrate High-Quality Speech Coding
15:30
Scaling Transformers for Low-Bitrate High-Quality Speech Coding
14 күн бұрын
Large Language Models as Markov Chains
33:17
Large Language Models as Markov Chains
14 күн бұрын
TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models
16:34
TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models
14 күн бұрын
ROICtrl: Boosting Instance Control for Visual Generation
13:22
ROICtrl: Boosting Instance Control for Visual Generation
14 күн бұрын
O1 Replication Journey -- Part 2
13:45
O1 Replication Journey -- Part 2
21 күн бұрын
O1 Replication Journey: A Strategic Progress Report -- Part 1
19:25
O1 Replication Journey: A Strategic Progress Report -- Part 1
21 күн бұрын
Star Attention: Efficient LLM Inference over Long Sequences
15:26
Star Attention: Efficient LLM Inference over Long Sequences
21 күн бұрын
Generative World Explorer
31:23
Generative World Explorer
21 күн бұрын
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
22:31
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
21 күн бұрын
Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
10:40
Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
21 күн бұрын
AnimateAnything: Consistent and Controllable Animation for Video Generation
20:22
AnimateAnything: Consistent and Controllable Animation for Video Generation
21 күн бұрын
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
17:39
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
28 күн бұрын
Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models
10:06
Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models
28 күн бұрын
Пікірлер