ST-BiBench reveals a coordination paradox in which MLLMs show strong high-level strategic reasoning yet fail at fine-grained 16-dimensional bimanual action synthesis and multi-stream fusion.
Taming preference mode collapse via directional decoupling alignment in diffusion reinforcement learning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
other 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5representative citing papers
MIGA introduces two-stage alignment to close train-inference gaps and dual consistency enhancement via self-reflection and long-range guidance to achieve SOTA temporal consistency in infinite-frame video generation on VBench and NarrLV.
By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.
E²PO uses embedding-level perturbations to maintain intra-group variance and discriminative signal in RL-based preference optimization for generative flow models.
The paper introduces the Proxy Compression Hypothesis as a unifying framework explaining reward hacking in RLHF as an emergent result of compressing high-dimensional human objectives into proxy reward signals under optimization pressure.
citing papers explorer
-
ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs
ST-BiBench reveals a coordination paradox in which MLLMs show strong high-level strategic reasoning yet fail at fine-grained 16-dimensional bimanual action synthesis and multi-stream fusion.
-
Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
MIGA introduces two-stage alignment to close train-inference gaps and dual consistency enhancement via self-reflection and long-range guidance to achieve SOTA temporal consistency in infinite-frame video generation on VBench and NarrLV.
-
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.
-
Embedding-perturbed Exploration Preference Optimization for Flow Models
E²PO uses embedding-level perturbations to maintain intra-group variance and discriminative signal in RL-based preference optimization for generative flow models.
-
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
The paper introduces the Proxy Compression Hypothesis as a unifying framework explaining reward hacking in RLHF as an emergent result of compressing high-dimensional human objectives into proxy reward signals under optimization pressure.