10 papers
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…
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…
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…
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…
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…