Jieping Ye

Principal Researcher@Alibaba Group·中国·OpenReview

研究方向

sparse learning · dimensionality reduction · multi-task learning · transfer learning · Out-of-distribution detection · multi-modal learning · machine learning · data mining

Jieping Ye

DrugTrail: Interpretable Drug Discovery via Structured Reasoning and Druggability‑Tailored Preference Optimization

Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs

PrismAudio: Decomposed Chain-of-Thought and Multi-dimensional Rewards for Video-to-Audio Generation

Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval

Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation

SPIDER: Multi-Layer Semantic Token Pruning and Adaptive Sub-Layer Skipping in Multimodal Large Language Models

EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer

Differential Fine-Tuning Large Language Models Towards Better Diverse Reasoning Abilities

MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models

DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations

Leveraging Potential Violation Elements for LVLM-based Image Content Moderation

How Do Language Models Speak Languages? A Case Study on Unintended Code-Switching

SchemaRAG: Enhancing Knowledge-Intensive Reasoning of LLMs via Inference-Time Adaptive Schema

AlignChat: Endowing LLMs with End-to-End Speech-to-Text Chat Capability through Token-Level Representation Alignment

Controlling Thinking Speed in Reasoning Models

EchoShot: Multi-Shot Portrait Video Generation

TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs

SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models

ROPO: Robust Preference Optimization for Large Language Models

Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models

Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding

ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL

Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs

Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering

Differential Fine-Tuning Large Language Models Towards Better Diverse Reasoning Abilities

Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language Models

AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models

Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization Approach

ROPO: Robust Preference Optimization for Large Language Models

Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger

Large Language Models Can Be More Robust Multiple Choice Selectors Through Attention Intervention

Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding

Structure-aware Domain Knowledge Injection for Large Language Models

PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Model

Deciphering and Enhancing Commonsense Reasoning in LLMs from the Perspective of Intrinsic Factual Knowledge Retrieval

Interpretable Analysis and Reasoning Enhancement for LLMs via Cross-Generation Reasoning Trees

Dynamic Alignment of Representations for Enhanced Chain-of-Thought Reasoning in Large Language Models

SciPIP: An LLM-based Scientific Paper Idea Proposer

Differentiation of Multi-objective Data-driven Decision Pipeline

Unveiling the Flow of Input-label Mappings for In-context Learning