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
3,821 results for “area:"applications to computer vision, audio, language, and other modalities"” in ICLR 2027. 1,646 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Generative co-evolution: rethinking weakly-supervised video highlight detection in the MLLM era▼4.5k2.67
[PDF]Still There, No Longer Seen: Exposing Compression-Induced Risk In Large Vision-Language Models▲5103.00
[PDF]Sampling Versus Longer Responses for Visual Reasoning: A Matched-Prompt MathVista Study▼1361.33
[PDF]PanoDPG: Decoupled Pose and Geometry Estimation for High-Resolution Panoramic 3D Reconstruction▲5.4k3.00
[PDF]FidPoster: End-to-End Product Poster Generation with Fine-grained Product Detail Fidelity▲3.8k2.50
[PDF]Free-to-Answer: Rethinking Output-Format Constraints in Reinforcement Fine-Tuning for Fine-Grained Visual Recognition▼1611.50
[PDF]Harmonia: Optimizing Aesthetic Gains within the Semantic Elasticity Boundary for Aesthetic Photo Reconstruction▲133.33
[PDF]A Unified Manifold Framework for Modeling Chinese Script Evolution with Application to Oracle Bone Decipherment▼4.3k2.00
[PDF]Rethinking Audio Visual Segmentation with Asymmetric Visual Entity Construction and Audio Querying▼4.3k2.00
[PDF]Structura: Intrinsic Scoring and Inference-Time Refinement against Structural Hallucinations in Video Generation▼5.8k2.33
[PDF]MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision▼5.8k2.33
[PDF]FireNav: Decision-Oriented Reconstruction Evidence Routing for Vision-Language Navigation in Indoor Fire Environments▼4.3k2.00
[PDF]ReVEAL: Eliciting Role-Aware Latent Visual Evidence from MLLMs for Reasoning Video Object Segmentation▼4.5k2.67
[PDF]GEOEPS: TRAINING-FREE EVIDENCE PRESENTATION AND SELECTION FOR ULTRA-HIGH-RESOLUTION REMOTE SENSING UNDERSTANDING▼4.5k2.67
[PDF]Decompose and Describe: Narrowing the Diagnosis-to-Report Gap in 3D CT Report Generation▼5.8k2.33
Withdrawn or desk rejected (1,646)
[PDF]Beyond Local Cycles: Long-Horizon Repetitive Action Counting via Multi-Scale Temporal Representation LearningDesk rejected
[PDF]Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal ModelsWithdrawn2.00