NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
63 results for “keyword:"chunk"” in ICLR 2027. 9 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Learning Chunk Values from Partial Execution in Offline-to-Online Reinforcement Learning▼5.8k2.33
[PDF]One Step Is Often Enough: Accelerating VLA Action Heads with Training-Free Marginal-Aligned Warm Starts▲4012.67
[PDF]Relative Temporal Alignment for Real-Time Execution of Vision-Language-Action Policies▼5.8k2.33
[PDF]GainPilot: Steering Vision-Language-Action Policies with Gain-Triggered Replanning and Bounded Action Correction▼4.3k2.00
[PDF]SWAP: Switched Action Chunking Policies with Massively Parallelized Multi-Task Reinforcement Learning▼1.2k3.00
[PDF]Effects of Token-level Loss Reweighting on Long-Range Recall in Chunked Training of Mamba-2▼1.2k1.67
[PDF]When can test-time search be skipped? Successor-Channel Criticality for Action-Chunked Policies▲4012.67
[PDF]Beyond Token Scale: Chunk-Level Sparse Autoencoders for Reliable Semantic Feature Discovery▲3.0k2.33
[PDF]Multi-Level Transformer: A Minimal Transformer Extension for Learned Sequence Chunking▲9.2k2.67
[PDF]MAX-Cache: Motion-Aligned Activation Reuse with Mismatch-Guided Selective Recomputation for Efficient Autoregressive Video Diffusion▲4012.67
[PDF]SparkVLA: Stop-Aware Hierarchical VLA with Adaptive Action Chunking for Long Horizon Manipulation▼4.5k2.67
[PDF]Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL▲1.7k3.33
[PDF]Revisiting Open-Loop Execution in Robotics: Toward Reactive, Higher-Performing Policies▼2433.33
Withdrawn or desk rejected (9)
[PDF]Fast Thinking, Steady Control: Coherent Action-Chunk Transitions for Real-Time VLA InferenceWithdrawn1.67
[PDF]UATL: Uncertainty-Aware Temporal Learning for Open-Loop Vision-Language-Action ControlWithdrawn1.67
[PDF]WAVE: World-Model-Augmented Value Learning for Action-Chunk Reinforcement LearningWithdrawn1.33
[PDF]Human Demonstrations and RL Data Yield Different Chunking Effectiveness: Activity Sparsity as a Key IndicatorWithdrawn1.33
[PDF]Temporal Ensembling Revisited: Recovering the Stochastic Headroom of Generative Robot PoliciesDesk rejected3.00