Picture for Tao Gui

Tao Gui

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use

Add code
Jan 07, 2025
Viaarxiv icon

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use

Add code
Dec 20, 2024
Viaarxiv icon

UniPaint: Unified Space-time Video Inpainting via Mixture-of-Experts

Add code
Dec 09, 2024
Viaarxiv icon

Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning

Add code
Dec 04, 2024
Figure 1 for Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning
Figure 2 for Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning
Figure 3 for Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning
Figure 4 for Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning
Viaarxiv icon

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Add code
Nov 25, 2024
Figure 1 for Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
Figure 2 for Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
Figure 3 for Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
Figure 4 for Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
Viaarxiv icon

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling

Add code
Nov 01, 2024
Viaarxiv icon

Multi-Programming Language Sandbox for LLMs

Add code
Oct 30, 2024
Figure 1 for Multi-Programming Language Sandbox for LLMs
Figure 2 for Multi-Programming Language Sandbox for LLMs
Figure 3 for Multi-Programming Language Sandbox for LLMs
Figure 4 for Multi-Programming Language Sandbox for LLMs
Viaarxiv icon

Distill Visual Chart Reasoning Ability from LLMs to MLLMs

Add code
Oct 24, 2024
Figure 1 for Distill Visual Chart Reasoning Ability from LLMs to MLLMs
Figure 2 for Distill Visual Chart Reasoning Ability from LLMs to MLLMs
Figure 3 for Distill Visual Chart Reasoning Ability from LLMs to MLLMs
Figure 4 for Distill Visual Chart Reasoning Ability from LLMs to MLLMs
Viaarxiv icon

Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs

Add code
Oct 20, 2024
Viaarxiv icon

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

Add code
Oct 15, 2024
Figure 1 for Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Figure 2 for Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Figure 3 for Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Figure 4 for Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Viaarxiv icon