Picture for Tong Xiao

Tong Xiao

Jack

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Add code
Dec 13, 2024
Viaarxiv icon

Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation

Add code
Dec 03, 2024
Viaarxiv icon

Early Exit Is a Natural Capability in Transformer-based Models: An Empirical Study on Early Exit without Joint Optimization

Add code
Dec 02, 2024
Viaarxiv icon

ProGraph: Temporally-alignable Probability Guided Graph Topological Modeling for 3D Human Reconstruction

Add code
Nov 07, 2024
Viaarxiv icon

Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning

Add code
Nov 05, 2024
Viaarxiv icon

TLDR: Token-Level Detective Reward Model for Large Vision Language Models

Add code
Oct 07, 2024
Figure 1 for TLDR: Token-Level Detective Reward Model for Large Vision Language Models
Figure 2 for TLDR: Token-Level Detective Reward Model for Large Vision Language Models
Figure 3 for TLDR: Token-Level Detective Reward Model for Large Vision Language Models
Figure 4 for TLDR: Token-Level Detective Reward Model for Large Vision Language Models
Viaarxiv icon

Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models

Add code
Oct 07, 2024
Figure 1 for Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models
Figure 2 for Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models
Figure 3 for Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models
Figure 4 for Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models
Viaarxiv icon

LRHP: Learning Representations for Human Preferences via Preference Pairs

Add code
Oct 06, 2024
Viaarxiv icon

A Modular-based Strategy for Mitigating Gradient Conflicts in Simultaneous Speech Translation

Add code
Sep 24, 2024
Figure 1 for A Modular-based Strategy for Mitigating Gradient Conflicts in Simultaneous Speech Translation
Figure 2 for A Modular-based Strategy for Mitigating Gradient Conflicts in Simultaneous Speech Translation
Figure 3 for A Modular-based Strategy for Mitigating Gradient Conflicts in Simultaneous Speech Translation
Figure 4 for A Modular-based Strategy for Mitigating Gradient Conflicts in Simultaneous Speech Translation
Viaarxiv icon

More Effective LLM Compressed Tokens with Uniformly Spread Position Identifiers and Compression Loss

Add code
Sep 22, 2024
Viaarxiv icon