Picture for Zilong Zheng

Zilong Zheng

Probing and Inducing Combinational Creativity in Vision-Language Models

Add code
Apr 17, 2025
Viaarxiv icon

OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts

Add code
Mar 29, 2025
Viaarxiv icon

MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge

Add code
Feb 27, 2025
Viaarxiv icon

Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs

Add code
Feb 26, 2025
Viaarxiv icon

From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens

Add code
Feb 26, 2025
Viaarxiv icon

LIFT: Improving Long Context Understanding of Large Language Models through Long Input Fine-Tuning

Add code
Feb 20, 2025
Viaarxiv icon

Causal Graph Guided Steering of LLM Values via Prompts and Sparse Autoencoders

Add code
Dec 31, 2024
Viaarxiv icon

How to Synthesize Text Data without Model Collapse?

Add code
Dec 19, 2024
Figure 1 for How to Synthesize Text Data without Model Collapse?
Figure 2 for How to Synthesize Text Data without Model Collapse?
Figure 3 for How to Synthesize Text Data without Model Collapse?
Figure 4 for How to Synthesize Text Data without Model Collapse?
Viaarxiv icon

LIFT: Improving Long Context Understanding Through Long Input Fine-Tuning

Add code
Dec 18, 2024
Viaarxiv icon

Mars: Situated Inductive Reasoning in an Open-World Environment

Add code
Oct 10, 2024
Figure 1 for Mars: Situated Inductive Reasoning in an Open-World Environment
Figure 2 for Mars: Situated Inductive Reasoning in an Open-World Environment
Figure 3 for Mars: Situated Inductive Reasoning in an Open-World Environment
Figure 4 for Mars: Situated Inductive Reasoning in an Open-World Environment
Viaarxiv icon