9 papers
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Mind Lab, :, Vin Bo +80
Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized arou…
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Changhai Zhou, Kieran Liu, Yuhua Zhou +17
Long-context RL post-training is constrained by the lifetime of state and gradients, not attention cost alone. In GRPO, one multi-million-token prompt must serve old-policy and ref…
CoBind: Stage-Aware Compositional Binding for Training-Free Text-to-Image Generation
Kaijie Chen, Ethan Caldwell, Mira Vossen +3
Diffusion-based text-to-image models often fail on complex prompts involving multiple entities, attributes, and relations, producing object omissions, incorrect attribute assignmen…
FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Drift
Kaijie Chen, Alex Johnson, Maria Garcia +2
This paper addresses the challenging problem of dynamic feature drift in federated learning, where data distributions evolve across clients and over time -- a common scenario in re…
STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning
Qinjian Zhao, Zhihao Dou, Dinggen Zhang +10
Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improving the reasoning abilities of large language models. However, existi…
SuperFlow: Training Flow Matching Models with RL on the Fly
Kaijie Chen, Zhiyang Xu, Ying Shen +3
Recent progress in flow-based generative models and reinforcement learning (RL) has improved text-image alignment and visual quality. However, current RL training for flow models s…
MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs
Huiyi Chen, Jiawei Peng, Dehai Min +5
Evaluating the robustness of Large Vision-Language Models (LVLMs) is essential for their continued development and responsible deployment in real-world applications. However, exist…
R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation
Kaijie Chen, Zihao Lin, Zhiyang Xu +5
Reasoning is a fundamental capability often required in real-world text-to-image (T2I) generation, e.g., generating ``a bitten apple that has been left in the air for more than a w…
EvoFlow: Evolving Diverse Agentic Workflows On The Fly
Guibin Zhang, Kaijie Chen, Guancheng Wan +5
The past two years have witnessed the evolution of large language model (LLM)-based multi-agent systems from labor-intensive manual design to partial automation (\textit{e.g.}, pro…