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
113 results for “keyword:"mllms"” in ICLR 2027. 52 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning▼4.5k2.67
[PDF]ActVis: Active Maintenance of Structured Visual Evidence for Efficient Visual Chain-of-Thought Reasoning▼1.2k1.67
[PDF]Block-Causal Encoding: Converting Large MLLM Encoders for Efficient On-Device Inference▲5.4k3.00
[PDF]CuE: A Cue Engineering Framework for Diagnosing and Mitigating Shortcut Effects on Zero-shot MLLM Recognition▲6.1k2.00
[PDF]WebMetaBench: Interactive Black-Box Testing as Multimodal Meta-Evaluation for Web Development Agents▼5.8k2.33
[PDF]AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents▼5.8k2.33
[PDF]DSE-GRPO: Differential Semantic Entropy for Debiased Noisy-Rollout Policy Optimization▼4.3k2.00
[PDF]1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World▼5.8k2.33
[PDF]The Evidence Anchoring Boundary: Where Visual Interventions Matter and When They Help in Multimodal LLMs▼5.8k2.33
[PDF]Understanding What You Point At: Spatial Guidance for Reference Disambiguation in Egocentric Video▲3952.67
[PDF]MobiGraph: Towards a Practical Evaluation Paradigm for Mobile Agents via Trajectory-Fused State Graphs▼4.5k2.67
[PDF]TAPD-SR: Bridging the Detail-Conditioning Gap for Diffusion-Based Faithful Real-World Image Super-Resolution▼4.3k2.00
[PDF]Where to Look, What to Keep: Two-Phase Learning for Grounding-Aware Visual Token Selection▲3952.67
[PDF]Enhancing Transferable Targeted Attacks on Closed-Source MLLMs with Progressive Semantic Chain▼4.3k2.00
[PDF]Closing the Curation Loop: Semantic Compression and Learning-Guided Expansion for MLLMs Mid-Training▲3952.67
[PDF]LEMMO: A Large Electromagnetic Model Leveraging Pretrained LLMs for Million-Sample Signal Understanding▼4.3k2.00
[PDF]SocialBench : Evaluating Multimodal Perception, Understanding and Reasoning in Social Settings▲3952.67
[PDF]CAER: Conflict-Aware Evidence Refinement for Knowledge-Based Visual Question Answering▼4.3k2.00
[PDF]FINE: Information Flow-Guided Intervention with Noise for Mitigating Text Dominance in Multimodal Large Language Models▼5.8k2.33
[PDF]SketchFactory: A Unified Framework for Learning and Evaluating Sketch-to-Code Generation▼5.8k2.33
[PDF]SciReC: Diagnostic Evaluation of Multimodal Multi-Turn Relational Reasoning with Adaptive Interaction▼5.8k2.33
[PDF]Optimizing Visualization for Time Series Analysis via Vision-embedded Bayesian Optimization▼5.8k2.33
[PDF]SyncPro: Synchronous Reasoning and Responding for Proactive Streaming Video Understanding▼5.8k2.33
[PDF]Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs▲4.6k3.00
Withdrawn or desk rejected (52)
[PDF]-VLM: Detecting and Correcting Vision-Language Hallucination via Active Representational Perturbation and Residual Spectral GroundingWithdrawn1.33
[PDF]Distilling One Token is Enough: Rethinking On-Policy Distillation for Visual Perception in MLLMsWithdrawn1.67
[PDF]SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image GenerationWithdrawn2.00
[PDF]InstructCD: A Unified Instruction-Following Framework for Remote Sensing Change DetectionWithdrawn2.00
[PDF]DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE InferenceDesk rejected2.33
[PDF]BAS-OPD: Budget-Aware Selective On-Policy Self-Distillation for Fine-Grained Multimodal PerceptionWithdrawn1.67