Qingfu Zhang

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training

Plug-and-Play Compositionality for Boosting Continual Learning with Foundation Models

Consistency Is Not Always Correct: Towards Understanding the Role of Exploration in Post-Training Reasoning

URS: A Unified Neural Routing Solver for Cross-Problem Zero-Shot Generalization

Hierarchical Representations for Cross-task Automated Heuristic Design using LLMs

Learning to Reduce Search Space for Generalizable Neural Routing Solver

Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies

GeoCMON: Operator Learning on Deformable Domains via Disentangled Geometric Conditioning

ARS: Automatic Routing Solver with Large Language Models

GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning

Fusing LLMs with Scientific Literature for Heuristic Discovery

Multi-Objective Bandits with Hierarchical Preferences: A Thompson Sampling Approach

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training

EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models

Deciphering the Extremes: A Novel Approach for Pathological Long-tailed Recognition in Scientific Discovery

TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition

Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data

Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization

Gradient-Guided Epsilon Constraint Method for Online Continual Learning

Neural Evolution Strategy for Black-box Pareto Set Learning

SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning

Learning to Insert for Constructive Neural Vehicle Routing Solver

Provable In-Context Vector Arithmetic via Retrieving Task Concepts

Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems

Multi-objective Linear Reinforcement Learning with Lexicographic Rewards

ICAM: Rethinking Instance-Conditioned Adaptation in Neural Vehicle Routing Solver

Partition to Evolve: Niching-enhanced Evolution with LLMs for Automated Algorithm Discovery

Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data

Multiobjective distribution matching

RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark