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
44 results for “keyword:"tokens"” in ICLR 2027. 9 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Links Are Tokens as Nodes Are: Incidence-Graph Transformers with Editable Walk Encodings for Link Prediction▼4.3k2.00
[PDF]What Is a Visual Thought Worth? When Continuous Visual States Help Vision-Language Models Reason▼4.3k2.00
[PDF]I Know That I Know Nothing: Narrowing the Knowledge-Output Gap in Large Language Models through Early High-Entropy Token Intervention▲3.0k2.33
[PDF]Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents▼4.3k2.00
[PDF]Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection▲5103.00
[PDF]Pelican-VLA 0.5: Inducing Transferable Manipulation-Centric Attention via Bottleneck Tokens▼3.7k2.25
[PDF]From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls▲153.33
[PDF]StrokeForm: Semantic Co-Speech Gesture Generation with Kinematically Grounded Motion Tokens▲5.4k3.00
[PDF]When to End, Which to Invoke Next: Transition-Aware Tokenized Procedural Memory for LLMs▲3.0k2.33
[PDF]Audio Tokens as a Budgeted Resource: Marginal-Utility Allocation for Scalable Audio Representations▼4.3k2.00
[PDF]Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision–Language Models▼4.5k2.67
[PDF]Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration▲3.0k2.50
[PDF]Coordination from Within: Decentralized Sequence Modeling for Multi-Agent Reinforcement Learning▼4.5k2.67
[PDF]LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery▼1.2k1.67
[PDF]Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?▼4.3k2.00
[PDF]SIGMA: Interaction-Conditioned Geometry Tokenization for Cross-Shape Humanoid Manipulation▲3.0k2.33
[PDF]DPR: From High-Entropy Tokens to Learning Claims — Matched Evaluation for Token-Selective LLM Reinforcement Learning▼1361.33
Withdrawn or desk rejected (9)
[PDF]Tokenizing the Unseen: Compact Visual Prefix Cache for Overcoming VLM Input BandwidthWithdrawn1.67
[PDF]SAGA: Spatially-Aware Gated Attention for Separating Outlier Structure from Functional Effect in Vision TransformersWithdrawn1.67
[PDF]Construction Confidence Need Not Be Verification Confidence: Round-Trip Verification and Selective Repair for Masked Diffusion SpeechWithdrawn1.75
[PDF]DeltaWAM: Change-Centric Visual Foresight via Delta Tokens for Efficient World-Action ModelWithdrawn1.67