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
356 results for “keyword:"raining free"” in ICLR 2027. 118 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]STEER: State-Transition Event Evidence Reasoning for Training-Free Video Temporal Grounding▼1.2k1.67
[PDF]Better Trajectories, Not More: Paired Posterior Correction for Flow-Matching Inverse Problems▼1.2k3.00
[PDF]PROVE: Training-Free Reference-Guided Pareto-Consensus Velocity Editing for Cross-Context Single-Cell Perturbation Prediction▼5.9k2.50
[PDF]Direct Trajectory Optimization for Inference-Time Alignment of Text-to-Image Diffusion Models▼1.2k1.67
[PDF]DGA-VLA: A Lightweight Depth-Guided Grasp Enhancement for VLA Models without Retraining▲11k2.00
[PDF]Rethinking Diffusion Caching: From Historical Extrapolation to Current-Observation Completion▲3.0k2.50
[PDF]Score Addition Is Not Composition: Closed-Form Path Corrections for Training-Free Composition of Pretrained Flows▲1.7k3.33
[PDF]Improving Tail-Class Diversity in Diffusion Models via Training-Free SNR-Adaptive Block Routing▲5.4k3.00
[PDF]SJD-VP: Speculative Jacobi Decoding with Verification Prediction for Autoregressive Image Generation▼5.8k2.33
[PDF]The Denoising Estimate Is a State Variable: Joint Refinement for Few-Step Flow Language Models▲5.4k3.00
[PDF]ZipSign: Training-Free Spatio-Temporal Token Compression for Sign Language Translation▼5.8k2.33
[PDF]They Know When They're Unsure: Confidence-Gated Acceptance as a Two-Sided Defense against Sycophancy in Video Language Models▼1.2k1.67
[PDF]EviNav: Evidence-Grounded Search and Active Verification for Training-Free Aerial Object Navigation▲432.75
[PDF]Lost in Pruning: Silent Multilingual Collapse and Training-Free Recovery for One-Shot MoE Pruning▼1.2k3.00
[PDF]When Does Cross-Examination Beat Self-Assessment? A Text-Surface Visibility Law for Training-Free Agent Trustworthiness▼1361.33
[PDF]Quality Signal Is Already There: Training-Free Cross-Domain IQA by Amplifying Latent Quality Direction in Frozen CLIP▲2623.67
[PDF]Weight-Dictionary Decomposition: Reading a Transformer's Residual Stream with Its Own Writes▼1361.33
[PDF]HT-SCD: Self-Contrastive Decoding via Hallucination Trajectories for Mitigating Object Hallucinations in LVLMs▼1361.33
[PDF]TFPrune: Pruning Visual Redundancy while Preserving Token Functions for Efficient VLMs▼4.3k2.00
[PDF]Prox: Training-Free FFN Activation Sparsification in LLMs via Approximate Intermediate-State Salience▲3952.67
[PDF]Support-Compiled Feature Folding: More Evidence at Lower Memory Across Tabular Foundation Models▼4.3k2.00
[PDF]EncoreMem: Re-encounter Verification of Region Memory for Training-Free Long Video Generation▲1.7k3.33
[PDF]Decoupling Source Preservation from Target Generation in Next-Scale Autoregressive Image Editing via Fixed-History Contrast
[PDF]Context Rot in Agent Trajectories: Evolving-State Maintenance Is the Hidden Bottleneck of Long-Context Agents▲3.9k1.67
[PDF]Unmask the State: State-Adaptive Strategy Selection for Masked Diffusion Language Models▼1.2k1.67
Withdrawn or desk rejected (118)
[PDF]TFAG-OVD: Training-Free Attribute-Guided Open-Vocabulary Detection via LLM Semantic CompositionWithdrawn1.67
[PDF]FlowFaceSwap: Training-free Video Face Swapping via Structure-Preserved Identity Flow EditingWithdrawn1.67
[PDF]Trace Forcing: Anchor Tokens in the KV Cache for Training-Free Long Video GenerationWithdrawn2.00
[PDF]Refine Before You Regress: Persistent Belief Refinement for Geometric Reasoning with Frozen VLMsWithdrawn1.33