14 papers
MemWM: Memory-Augmented Text-Based World Model
Yujun Wang, Tao Zhang, Jinhe Bi +9
World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can sti…
MAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy
Aniri, Chen Yilin, Jinhe Bi +10
Vision-Language-Action models (VLAs) integrate visual perception, language instruction, and action generation into end-to-end policies across heterogeneous architectures. However,…
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
Aniri, Jinhe Bi, Peng Liao +5
On-Policy Self-Distillation (OPSD) has become a standard post-training approach for improving visual reasoning in multimodal large language models (MLLMs). Existing methods draw pr…
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Jinhe Bi, Chennan Zhou, Zengjie Jin +10
On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories…
Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models
Shengqiang Zhang, Ruotong Liao, Volker Tresp +2
Text-guided image editing with visual autoregressive (VAR) generators requires controlling both what the model samples and where the sampled change is written back into the image c…
TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation
Ruotong Liao, Guowen Huang, Qing Cheng +6
Text-to-video (T2V) generation faces challenging questions when generating videos with long horizons containing multiple events. Inspired by the intrinsics of the diffusion process…
EchoRL: Reinforcement Learning via Rollout Echoing
Jinhe Bi, Aniri, Minglai Yang +9
Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceed…
ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay
Gengyuan Zhang, Mingcong Ding, Jingpei Wu +2
Embodied exploration is a target-driven process that requires embodied agents to possess fine-grained perception and knowledge-enhanced decision making. While recent attempts lever…
Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
Thomas Decker, Volker Tresp, Florian Buettner
Perturbation-based explanations are widely utilized to enhance the transparency of machine-learning models in practice. However, their reliability is often compromised by the unkno…
When and Where do Events Switch in Multi-Event Video Generation?
Ruotong Liao, Guowen Huang, Qing Cheng +3
Text-to-video (T2V) generation has surged in response to challenging questions, especially when a long video must depict multiple sequential events with temporal coherence and cont…
Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations
Thomas Decker, Volker Tresp, Florian Buettner
Perturbation-based explanations are widely utilized to enhance the transparency of modern machine-learning models. However, their reliability is often compromised by the unknown mo…
AViLA: Asynchronous Vision-Language Agent for Streaming Multimodal Data Interaction
Gengyuan Zhang, Tanveer Hannan, Hermine Kleiner +6
An ideal vision-language agent serves as a bridge between the human users and their surrounding physical world in real-world applications like autonomous driving and embodied agent…
Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention
Alexander Koebler, Thomas Decker, Ingo Thon +2
We study the problem of monitoring machine learning models under gradual distribution shifts, where circumstances change slowly over time, often leading to unnoticed yet significan…
Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance
Thomas Decker, Alexander Koebler, Michael Lebacher +3
Monitoring and maintaining machine learning models are among the most critical challenges in translating recent advances in the field into real-world applications. However, current…