13 papers
Do Rollups Self-Organize? Multi-Agent Reinforcement Learning in the EIP-4844 Blob Fee Market
Alessio Brini
EIP-4844 gave Ethereum rollups a separate fee dimension for data, governed by a multiplicative update rule that targets three ``blobs'' per block. Whether this target is reached de…
Correcting WHERE, Preserving HOW: Compositional Generalization for Vision-Language-Action Models via Referential Guidance
Yanyan Zhang, Disheng Liu, Xinpeng Li +8
While Vision-Language-Action (VLA) models enable flexible action generation, their generalization across diverse environmental elements, including manipulated objects, destinations…
Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting
Disheng Liu, Tuo Liang, Chaoda Song +1
Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models. Existing approaches to exploiting this potentia…
Imagining Recovery: Inference-Time Counterfactual Realignment for Vision-Language-Action Models
Yanyan Zhang, Disheng Liu, Kai Ye +6
Vision-language-action (VLA) models have improved the flexibility and generality of robotic manipulation, yet they remain fragile to online disruptions, such as changes in task goa…
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…
CausalGuard: Conformal Inference under Graph Uncertainty
Vikash Singh, Weicong Chen, Debargha Ganguly +12
Estimating treatment effects from observational data requires choosing an adjustment set, but valid adjustment depends on an unknown causal graph. Graph misspecification can cause…
Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models
Yanyan Zhang, Chaoda Song, Vikash Singh +6
Vision-Language-Action (VLA) models achieve remarkable flexibility and generalization beyond classical control paradigms. However, most prevailing VLAs are trained under a single-f…
AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments
Wang Yang, Chaoda Song, Xinpeng Li +7
Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41\% of total evaluation time) and imbalanced task horizon and difficul…
Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation
Shouren Wang, Wang Yang, Chuang Ma +7
Hybrid-thinking language models expose explicit /think and /no_think modes, but current designs do not separate them cleanly. Even in /no_think mode, models often emit long and sel…
CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAG
Nengbo Wang, Tuo Liang, Vikash Singh +6
Retrieval augmented generation (RAG) has enhanced large language models by enabling access to external knowledge, with graph-based RAG emerging as a powerful paradigm for structure…
When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning
Wang Yang, Shouren Wang, Chaoda Song +6
Group Relative Policy Optimization (GRPO) has become a key technique for improving reasoning abilities in large language models, yet its behavior under different domain sequencing…
Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
Wang Yang, Debargha Ganguly, Xinpeng Li +5
Hybrid reasoning language models are commonly controlled through high-level Think/No-think instructions to regulate reasoning behavior, yet we found that such mode switching is lar…
Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting
Yiren Lu, Yunlai Zhou, Yiran Qiao +5
Open-vocabulary querying in 3D space is crucial for enabling more intelligent perception in applications such as robotics, autonomous systems, and augmented reality. However, most…