Tao Feng
- Papers
- 21
Cite
Notes
Only stored in your browser.
Authored papers
21MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
arXiv 2026
Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Survey
arXiv 2026
Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
arXiv 2026
RouteProfile: Graph-Based Profiling for Cold-Start LLM Routing
arXiv 2026
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
arXiv 2026
Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
arXiv 2025
Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
arXiv 2025
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
arXiv 2025
GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts
arXiv 2025
Lumos-1: On Autoregressive Video Generation from a Unified Model Perspective
arXiv 2025
IRanker: Towards Ranking Foundation Model
arXiv 2025
MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
arXiv 2025
Parameter-Efficient Fine-Tuning for Foundation Models
arXiv 2025
A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models
arXiv 2025
Adapt before Continual Learning
arXiv 2025
Revisiting Neural Networks for Continual Learning: An Architectural Perspective
arXiv 2024
How Far Are We From AGI: Are LLMs All We Need?
arXiv 2024
ResearchTown: Simulator of Human Research Community
arXiv 2024
GraphRouter: A Graph-based Router for LLM Selections
arXiv 2024
Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs
arXiv 2024
RLIPv2: Fast Scaling of Relational Language-Image Pre-training
ICCV 2023 1
Affiliations
Frequent co-authors
10from 21 papers