ICLR 2026 - Submissions

SubmissionsReviews

Submissions

Quantity AI Content: 0-10%10-30%30-50%50-70%70-90%90-100%All
Avg Rating: 0-11-22-33-44-55-66-77-88-99-10All

Summary Statistics

Quantity AI Content Count Avg Rating
0-10% 11864 (61%) 4.36
10-30% 3952 (20%) 4.14
30-50% 1846 (9%) 3.93
50-70% 1026 (5%) 3.75
70-90% 494 (3%) 3.39
90-100% 199 (1%) 2.90
Total 19490 (100%) 4.20
Title Abstract Avg Rating Quantity AI Content Reviews Pangram Dashboard
Pick Your Channel: Ultra-Sparse Readouts for Recovering Functional Cell Types Clustering neurons into distinct functional cell types is a prominent approach to understand how the brain integrates information about the external world. In recent years, digitial-twins of the visua... 3.33 1% See Reviews View AI Dashboard
DyRo-MCTS: A Robust Monte Carlo Tree Search Approach to Dynamic Job Shop Scheduling Dynamic job shop scheduling, a fundamental combinatorial optimisation problem in various industrial sectors, poses substantial challenges for effective scheduling due to frequent disruptions caused by... 4.00 6% See Reviews View AI Dashboard
FLoRA-NA: Nearly Accurate Aggregation for Federated Low-Rank Adaptation With the rapid emergence of foundation models and the increasing need for fine-tuning across distributed environments, Federated Low-Rank Adaptation (FedLoRA) has recently gained significant attention... 4.00 2% See Reviews View AI Dashboard
LVCap-Eval: Towards Holistic Long Video Caption Evaluation for Multimodal LLMs Generating coherent and factually grounded captions for long-form videos is a critical yet underexplored challenge for multimodal large language models (MLLMs). Existing benchmarks, which predominantl... 3.50 14% See Reviews View AI Dashboard
Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers Recent advances in diffusion models have significantly improved image editing. However, challenges persist in handling geometric transformations, such as translation, rotation, and scaling, particular... 5.33 12% See Reviews View AI Dashboard
Single-Sample Test-Time Reinforcement Learning for Vision-Language Models While Test-Time Reinforcement Learning (TTRL) has shown promise for adapting language models without ground truth answers, its application to vision-language tasks remains unexplored. Similarly, exist... 4.50 47% See Reviews View AI Dashboard
Causally Disentangled World Models: Guiding Exploration with an Agency Bonus Model-Based Reinforcement Learning (MBRL) promises to improve sample efficiency, yet conventional world models learn a purely observational, black-box model of dynamics. This leads to causal confoundi... 3.00 64% See Reviews View AI Dashboard
$\mu$LO: Compute-Efficient Meta-Generalization of Learned Optimizers Learned optimizers (LOs) have the potential to significantly reduce the wall-clock training time of neural networks. However, they can struggle to optimize unseen tasks (*meta-generalize*), especially... 5.00 0% See Reviews View AI Dashboard
Extracting Rule-based Descriptions of Attention Features in Transformers Mechanistic interpretability strives to explain model behavior in terms of bottom-up primitives. The leading paradigm is to express hidden states as a sparse linear combination of basis vectors, calle... 4.00 0% See Reviews View AI Dashboard
AI Respondents for Policy Monitoring: From Data Extraction to AI-Driven Survey Responses in the OECD STIP Compass Science, Technology, and Innovation (STI) policies are central to national and international competitiveness, yet their complexity makes systematic mapping and continuous monitoring a persistent chall... 2.00 35% See Reviews View AI Dashboard
Mitigating Hallucination in Multimodal Reasoning via Functional Attention Control Multimodal large reasoning models (MLRMs) are rapidly advancing vision-language reasoning and are emerging as a foundation for cross-modal intelligence. Hallucination remains a persistent failure mod... 3.33 4% See Reviews View AI Dashboard
Iterative Importance Fine-tuning of Diffusion Models Diffusion models are an important tool for generative modelling, serving as effective priors in applications such as imaging and protein design. A key challenge in applying diffusion models for downst... 4.00 0% See Reviews View AI Dashboard
Learning to Remember, Learn, and Forget in Attention-Based Models The ability to perform learning during inference, i.e. in-context learning (ICL) is a core feature of self-attention in transformers. ICL acts like an online associative memory and is believed to und... 3.00 0% See Reviews View AI Dashboard
Learning Admissible Heuristics for A*: Theory and Practice Heuristic functions are central to the performance of search algorithms such as A*, where \emph{admissibility}—the property of never overestimating the true shortest-path cost—guarantees solution opti... 5.71 0% See Reviews View AI Dashboard
Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction The transcriptional response to genetic perturbation reveals fundamental insights into complex cellular systems. While current approaches have made progress in predicting genetic perturbation response... 4.50 0% See Reviews View AI Dashboard
Sharp Monocular View Synthesis in Less Than a Second We present SHARP, an approach to photorealistic view synthesis from a single image. Given a single photograph, SHARP regresses the parameters of a 3D Gaussian representation of the depicted scene. Thi... 5.00 9% See Reviews View AI Dashboard
Neuro-Symbolic VAEs for Temporal Point Processes: Logic-Guided Controllable Generation In safety-critical domains such as healthcare, sequential data (e.g., patient trajectories in electronic health records) are often sparse, incomplete, and privacy-sensitive, limiting their utility for... 4.00 60% See Reviews View AI Dashboard
Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Synergizing-Oriented Multi-Turn Reinforcement Learning Compressing long chain-of-thought (CoT) from large language models (LLMs) is an emerging strategy to improve the reasoning efficiency of LLMs. Despite its promising benefits, existing studies equally ... 3.50 0% See Reviews View AI Dashboard
Measuring Meta-Cultural Competency: A Spectral Framework for LLM Knowledge Structures Most cultural evaluation frameworks for Large Language Models (LLMs) compare model outputs with ground-truth answers, capturing mainly factual awareness. This overlooks whether models internalize broa... 5.00 10% See Reviews View AI Dashboard
GCSGNN: Towards Global Counterfactual-Based Self-Explainable Graph Neural Networks Graph Neural Networks (GNNs) exhibit superior performance in various graph-based tasks, ranging from scene graph generation to drug discovery. However, they operate as black-box models due to the lack... 4.00 0% See Reviews View AI Dashboard
Search-T2I: Internet-Augmented Text-to-Image Generation Current text-to-image (T2I) generation models achieve promising results, but they fail on the scenarios where the knowledge implied in the text prompt is uncertain. For example, a T2I model released i... 3.50 0% See Reviews View AI Dashboard
DMark: Order-Agnostic Watermarking for Diffusion Large Language Models Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequent... 3.00 60% See Reviews View AI Dashboard
Beyond Weight-Only: Mixed-Precision Quantization for BERT Weights, Activations and Embeddings Pre-trained language models deliver strong performance across various Natural Language Processing (NLP) tasks but remain costly to deploy due to memory and compute demands. To address this, model comp... 2.00 0% See Reviews View AI Dashboard
Prompt Engineering at Scale: Provably Effective Multi-Agent Cascades for Attribute Generation in E-Commerce Developing specialized Large Language Model (LLM) prompts for domain-specific tasks at scale remains a significant hurdle, particularly for e-commerce applications managing tens of thousands of distin... 3.50 52% See Reviews View AI Dashboard
Locality-Aware Multiresolution Graph Spectral Filtering to Mitigate Oversmoothing and Oversquashing. Real-world graphs demonstrate region-specific heterophily: some regions are smooth and suitable for low-pass averaging, whereas others are sharp and necessitate high-pass contrast. However, spectral ... 3.20 0% See Reviews View AI Dashboard
Robust Bidirectional Associative Memory via Regularization Inspired by the Subspace Rotation Algorithm Bidirectional Associative Memory (BAM) trained by Bidirectional Backpropagation (B-BP) suffer from poor robustness and sensitivity to noise and adversarial attacks. To address it, we propose a novel g... 4.40 10% See Reviews View AI Dashboard
Log Probability Tracking of LLM APIs When using an LLM through an API provider, users expect the served model to remain consistent over time, a property crucial for the reliability of downstream applications and the reproducibility of re... 5.33 0% See Reviews View AI Dashboard
Adaptive Mixing of Non-Invariant Information for Generalized Diffusion Policy Diffusion policies (DP) have emerged as a leading paradigm for learning-based robotic manipulation, offering temporally coherent action synthesis from high-dimensional observations. However, despite ... 2.00 41% See Reviews View AI Dashboard
Graph Attention with Knowledge-Aware Domain Adaptation for Drug-Target Interaction Prediction Predicting drug-target interactions (DTIs) under domain shift is a central challenge in data-driven drug discovery. In this context, we suggest DTI-DA, a practical framework which combines (i) a Graph... 2.50 9% See Reviews View AI Dashboard
PELICAN: Personalized Education via LLM-powered Cognitive Diagnosis and Adaptive Tutoring Personalized education aims to develop students' engagement, critical thinking and deep understanding through tailored teaching strategies. Although Large Language Models (LLMs) have generated signifi... 5.00 12% See Reviews View AI Dashboard
Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models Data visualizations are vital components of many scientific articles and news stories. Current vision-language models (VLMs) still struggle on basic data visualization understanding tasks, but the cau... 4.50 0% See Reviews View AI Dashboard
Evaluating Explanatory Evaluations: An Explanatory Virtues Framework for Mechanistic Interpretability Mechanistic Interpretability (MI) aims to understand neural networks through causal explanations. Though MI has many explanation-generating methods and associated evaluation metrics, progress has been... 3.00 0% See Reviews View AI Dashboard
GSPRec: Temporal-Aware Graph Spectral Filtering for Recommendation Graph-based recommendation systems are effective at modeling collaborative patterns but often suffer from two limitations: overreliance on low-pass filtering, which suppresses user-specific signals, a... 4.00 34% See Reviews View AI Dashboard
DPMFormer: Dual-Path Mamba-Transformer for Efficient Image Super‑Resolution Vision Transformers have achieved outstanding performance in image super-resolution (SR), but existing lightweight models rely on window-based attention, limiting their ability to model global depende... 3.50 9% See Reviews View AI Dashboard
SADUNs: Sharpness-Aware Deep Unfolding Networks for Image Restoration The ability to improve model performance while preserving structural integrity represents a fundamental challenge in deep unfolding networks (DUNs), particularly when handling increasingly complex bla... 3.33 0% See Reviews View AI Dashboard
AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion Complementarity Determining Regions (CDRs) are critical segments of an antibody that facilitate binding to specific antigens. Current computational methods for CDR design utilize reconstruction losses... 5.00 4% See Reviews View AI Dashboard
VideoGameBench: Can Vision-Language Models complete popular video games? Vision-language models (VLMs) have achieved strong results on coding and math benchmarks that are challenging for humans, yet their ability to perform tasks that come naturally to humans--such as perc... 3.00 10% See Reviews View AI Dashboard
Semantic Calibration in Media Streams Current generative models can produce synthetic media that is visually indistinguishable from real content. As a result, traditional detection methods rely mostly on subtle artifacts introduced during... 4.67 3% See Reviews View AI Dashboard
From Editor to Dense Geometry Estimator Leveraging visual priors from pre-trained text-to-image (T2I) generative models has shown success in dense prediction. However, dense prediction is inherently an image-to-image task, suggesting that i... 4.00 0% See Reviews View AI Dashboard
EXPLOITING TREE STRUCTURE FOR CREDIT ASSIGNMENT IN RL TRAINING OF LLMS Reinforcement learning improves LLM reasoning, yet sparse delayed reward over long sequences makes token-level credit assignment the key bottleneck. We study the verifiable-reward setting, where the f... 3.00 33% See Reviews View AI Dashboard
OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds Multimodal large language models are progressively advancing toward multimodal agents that can proactively execute tasks. Existing research on multimodal agents primarily targets either GUI or embodie... 6.00 0% See Reviews View AI Dashboard
PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning Among various on-policy reinforcement learning algorithms, Proximal Policy Optimization (PPO) demonstrates its unparalleled simplicity, numerical stability, and empirical performance. It optimizes pol... 4.50 19% See Reviews View AI Dashboard
From Cheap Geometry to Expensive Physics: Elevating Neural Operators via Latent Shape Pretraining Industrial design evaluation often relies on high-fidelity simulations of governing partial differential equations (PDEs). While accurate, these simulations are computationally expensive, making dense... 4.50 0% See Reviews View AI Dashboard
EdgeMask-HGNN: Learning to Sparsify Hypergraphs for Scalable Node Classification in Hypergraph Neural Networks Hypergraph Neural Networks (HGNNs) have achieved remarkable performance in various learning tasks involving hypergraphs— a data model for higher-order relationships across diverse domains and applicat... 3.00 0% See Reviews View AI Dashboard
Deterministic Discrete Denoising We propose a deterministic denoising algorithm for discrete-state diffusion models based on Markov chains. The generative reverse process is derandomized by introducing a variant of the herding algori... 2.50 0% See Reviews View AI Dashboard
Fine-Grained Safety Neurons with Training-Free Continual Projection to Reduce LLM Fine Tuning Risks Fine-tuning as service injects domain-specific knowledge into large language models (LLMs), while challenging the original alignment mechanisms and introducing safety risks. A series of defense strat... 4.00 1% See Reviews View AI Dashboard
FedRKMGC: Towards High-Performance Gradient Correction-based Federated Learning via Relaxation and Fast KM Iteration Federated learning (FL) enables multiple clients to collaboratively train machine learning models without sharing their local data, providing clear advantages in terms of privacy and scalability. Howe... 5.33 38% See Reviews View AI Dashboard
Can LLMs be Fooled: A Textual Adversarial Attack method via Euphemism Rephrase to Large Language Models Large Language Models (LLMs) have shown their great power in addressing masses of challenging problems in various areas, including textual adversarial attack and defense. With the fast evolution of LL... 2.67 32% See Reviews View AI Dashboard
D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models Test-time adaptation paradigm provides flexibility towards domain shifts by performing immediate adaptation on unlabeled target data from the source model. Vision-Language Models (VLMs) leverage their... 4.50 0% See Reviews View AI Dashboard
PISCES: Annotation-free Text-to-Video Post-Training via Bi-objective OT-aligned Rewards Text-to-video (T2V) generation aims to synthesize videos with high visual quality and temporal consistency that are semantically aligned with input text. Reward-based post-training has emerged as a pr... 5.33 9% See Reviews View AI Dashboard
PreviousPage 3 of 390 (19490 total rows)Next