38:55

[Paper Review] Can Large Language Model Agents Simulate Human Trust Behavior?

37:29

[Paper Review] SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval

01:07:03

[Paper Review] KAN: Kolmogorov-Arnold Networks

45:20

[Paper Review] VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation

40:57

[Paper Review] Periodicity Decoupling Framework for Long-term Series Forecasting

34:18

[Paper Review] One-stage Prompt-based Continual Learning

37:56

[Paper Review] Continuous Memory Representation for Anomaly Detection

51:18

[Paper Review] A-LLMRec

41:36

[Paper Review] ReFormer: The Relational Transformer for Image Captioning

41:08

[Paper Review] RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for AD

56:20

[Paper Review] TIME-MOE: BILLION-SCALE TIME SERIES FOUNDATION MODELS WITH MIXTURE OF EXPERTS

28:29

[Paper Review] VISION TRANSFORMERS NEED REGISTERS

43:22

[Paper Review] VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection

35:54

[Paper Review] Chain-of-Thought Prompting in ACL 2024

36:36

[Paper Review] Recommender Systems with Generative Retrieval

41:21

[Paper Review] SensitiveHUE: MTSAD by Enhancing the Sensitivity to Normal Patterns

37:34

[Paper Review] Gecko: Versatile Text Embeddings Distilled from Large Language Models

31:04

[Paper Review] Cumulative Reasoning with Large Language Models

36:13

Transformer-based Multivariate TimeSeries Anomaly Detection using Inter-Variable Attention Mechanism

44:41

[Paper Review] AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection

29:16

[Paper Review] Affective-NLI: Towards Accurate Interpretable Personality Recognition in Conversation

47:09

[Paper Review] Less is More:Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder

49:15

[Paper Review] Koopman Neural Operator Forecaster for Time-series with Temporal Distribution Shifts

29:01

[Paper Review] CLIP3D-AD: Extending CLIP for 3D Few Shot Anomaly Detection

37:40

[Paper Review] Revisiting Active Learning in the Era of Vision Foundation Models

34:02

[Paper Review] Introducing Language Guidance in Prompt-based Continual Learning

16:02

[Paper Review] Caption Re-ranking Evaluation Using Ensembled CLIP and Consensus Scores

36:06

[Paper Review] How Abilities in Large Language Models are Affected by SFT Data Composition

01:00:04

[Paper Review] Tell Me More! Towards Implicit User Intention Understanding of Language Model Agent

29:12

[Paper Review] GLAD

33:36

[Paper Review] The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

36:40

[Paper Review] AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection

27:40

[Paper Review] ORPO: Monolithic Preference Optimization without Reference Model

22:22

[Paper Review] Contrastive Vision-Language Pre-training with Limited Resources

29:49

[Paper Review]CoLLM: Integrating Collaborative Embeddings into LLMs for Recommendation

34:03

[Paper Review] MeaCap: Memory-Augmented Zero-shot Image Captioning

17:11

[Paper Review] FT-LLM: 축구 산업의 데이터 분석 지원을 위한Retrieval 증강 생성 기반의 언어 모델 프레임워크 개발

25:14

[Paper Review] CHAMP: A Competition Dataset for Fine-Grained Analyses of LLMs' Math Reasoning

36:54

[Paper Review] LogFormer: A Pre-train and Tuning Pipeline for Log Anomaly Detection

59:36

[Paper Review] FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

30:34

[Paper Review] DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training

49:08

[Paper Review] Frequency-domain MLPs are More Effective Learners in Time Series Forecasting

34:34

[Paper review] Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt

45:23

[Paper Review] Shape-Guided Dual-Memory Learning for 3D Anomaly Detection

43:30

[Paper Review] Self supervised Feature Adaptation for 3D Industrial Anomaly Detection

41:12

[Paper Review]LLaRA:Large Language Recommendation Assistant

47:11

[Paper Review] SelectAL

53:58

[Paper Review] EXPLAINABLE TIME SERIES ANOMALY DETECTION USING MASKED LATENT GENERATIVE MODELING

46:15

[Paper Review] REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Knowledge Memory

43:09

[Paper Review] Interpreting CLIP's Image Representation via Text-Based Decomposition

25:09

[Paper Review] VCR-GRAPHORMER: A MINI-BATCH GRAPH TRANSFORMERVIA VIRTUAL CONNECTIONS

28:20

[Paper Review] Goal-Driven Explainable Clustering via Language Descriptions

37:49

[Paper Review] Scaling Data-Constrained Language Models

46:30

[Paper Review] From Similarity to Superiority: Channel Clustering for Time Series Forecasting

18:45

[Paper Review] Proxy-based Item Representation for Attribute and Context-aware Recommendation

30:29

[Paper Review] EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory

28:39

[Paper Review]Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

31:11

[Paper Review] iTransformer: Inverted Transformers Are Effective for Time Series Forecasting

28:31

[Paper Review]Generate rather than Retrieve: Large Language Models are Strong Context Generators

27:19

[Paper Review] ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs