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
Multi-Sample Preference Optimization for Generative Model Alignment Recent advancements in generative models, particularly large language models (LLMs) and diffusion models, have been driven by extensive pre-training on large datasets followed by post-training. Howeve... 4.00 0% See Reviews View AI Dashboard
SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier Functions Generative planners based on Flow Matching (FM) produce high-quality paths in a single or a few ODE steps, but their sampling dynamics offer no formal safety guarantees and can yield incomplete paths ... 6.00 0% See Reviews View AI Dashboard
Principled Latent Diffusion for Graphs via Laplacian Autoencoders Graph diffusion models achieve state-of-the-art performance in graph generation but suffer from quadratic complexity in the number of nodes---and much of their capacity is wasted modeling the absence ... 4.50 0% See Reviews View AI Dashboard
CGTFra: General Graph Transformer Framework for Consistent Inter-series Dependency Modeling in Multivariate Time Series Transformers have emerged as dominant predictors in multivariate time series forecasting (MTSF), prompting an in-depth investigation into their limitations within this application. Firstly, the conven... 4.00 0% See Reviews View AI Dashboard
MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging Simulating in silico cellular responses to interventions is a promising direction to accelerate high-content image-based assays, critical for advancing drug discovery and gene editing. To support this... 4.00 17% See Reviews View AI Dashboard
OpenAVS: Training-Free Open-Set Audio Visual Segmentation with Foundational Models Audio-visual segmentation (AVS) aims to separate sounding objects from videos by predicting pixel-level masks based on audio signals. Existing methods primarily concentrate on closed-set scenarios and... 3.50 0% See Reviews View AI Dashboard
Teach to Reason Safely: Policy-Guided Safety Tuning for MLRMs Multimodal Large Reasoning Models (MLRMs) have exhibited remarkable capabilities in complex multimodal tasks. However, our findings reveal a critical trade-off: reasoning-based models are more prone t... 4.50 37% See Reviews View AI Dashboard
AQuA: Toward Strategic Response Generation for Ambiguous Visual Questions Visual Question Answering (VQA) is a core task for evaluating the capabilities of Vision–Language Models (VLMs). Existing VQA benchmarks primarily feature clear and unambiguous image–question pairs, w... 5.50 17% See Reviews View AI Dashboard
LaVCa: LLM-assisted Visual Cortex Captioning Understanding the properties of neural populations (or voxels) in the human brain can advance our comprehension of human perceptual and cognitive processing capabilities and contribute to developing b... 5.50 0% See Reviews View AI Dashboard
Salient Object Ranking via Cyclical Perception-Viewing Interaction Modeling Salient Object Ranking (SOR) aims to predict human attention shifts across different salient objects in a scene. Although a number of methods have been proposed for the task, they typically rely on mo... 5.33 10% See Reviews View AI Dashboard
RECTOR: Masked Region-Channel-Temporal Modeling for Cognitive Representation Learning Affective and cognitive disorders are characterized by complex, distributed brain network dynamics across distinct functional regions, channels, and time, posing a significant challenge to learning ro... 3.50 0% See Reviews View AI Dashboard
Constructing a 3D Scene from a Single Image Acquiring detailed 3D scenes typically demands costly equipment, multi-view data, or labor-intensive modeling. Therefore, a lightweight alternative, generating complex 3D scenes from a single top-down... 5.50 20% See Reviews View AI Dashboard
LeGIT: LLM Guided Intervention Targeting for Online Causal Discovery A fundamental challenge in online causal discovery is designing effective experiments by selecting optimal intervention targets. Conventional numerical methods struggle in the early stages when limite... 3.50 5% See Reviews View AI Dashboard
Symmetric Behavior Policy Optimization Behavior Regularized Policy Optimization (BRPO) leverages asymmetric (divergence) regularization to mitigate the distribution shift in offline Reinforcement Learning. This paper is the first to study... 4.00 0% See Reviews View AI Dashboard
VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLMs) into their policy backbone, are gaining significant attention for their promising generalization cap... 7.00 0% See Reviews View AI Dashboard
EgoExo-Con: Exploring View-Invariant Video Temporal Understanding Can Video-LLMs achieve consistent temporal understanding when videos capture the same event from different viewpoints? To study this, we introduce EgoExo-Con (Consistency), a benchmark of comprehensiv... 4.50 5% See Reviews View AI Dashboard
Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions The Job Shop Scheduling Problem (JSP) and Flexible Job Shop Scheduling Problem (FJSP) are combinatorial optimization problems with wide-ranging applications in industrial operations. In recent years, ... 5.50 N/A See Reviews
Activation-Guided Regularization: Improving Deep Classifiers using Feature-Space Regularization with Dynamic Prototypes The softmax cross-entropy loss, which is the de facto standard for training deep classifiers, does not explicitly guide the formation of a well-structured internal feature space. This can limit model ... 2.50 70% See Reviews View AI Dashboard
FedMAP: Meta-Driven Adaptive Differential Privacy for Federated Learning Federated learning (FL) enables multiple clients to train a shared model without sharing raw data, but gradients can still leak sensitive information through inversion and membership inference attacks... 3.00 62% See Reviews View AI Dashboard
SPO: A Black-box, Unbiased, Robust Watermarking Method for Large Language Model Large language models (LLMs) have revolutionary impacts on text generation. Despite their widespread application, LLMs raise significant ethical and security concerns about potential misuse, such as f... 3.50 0% See Reviews View AI Dashboard
Good allocations from bad estimates Conditional average treatment effect (CATE) estimation is the de facto gold standard for targeting a treatment to a heterogeneous population. The method estimates treatment effects up to an error $\ep... 6.00 0% See Reviews View AI Dashboard
DFCA: Decentralized Federated Clustering Algorithm Clustered Federated Learning has emerged as an effective approach for handling heterogeneous data across clients by partitioning them into clusters with similar or identical data distributions. Howeve... 2.50 5% See Reviews View AI Dashboard
Black-box Optimization of LLM Outputs by Asking for Directions We present a novel approach for attacking black-box large language models (LLMs) by exploiting their ability to express confidence in natural language. Existing black-box attacks require either access... 4.50 27% See Reviews View AI Dashboard
Multivariate Time Series Forecasting with Fourier Neural Filter Multivariate time series forecasting has been suffering from the challenge of capturing both temporal dependencies within variables and spatial correlations across variables simultaneously. Current ap... 4.00 4% See Reviews View AI Dashboard
Binary-Integer-Programming Based Algorithm for Expert Load Balancing in Mixture-of-Experts Models For pre-training of MoE (Mixture-of-Experts) models, one of the main issues is unbalanced expert loads, which may cause routing collapse or increased computational overhead. Existing methods contain t... 3.33 0% See Reviews View AI Dashboard
Should We Forget About Certified Unlearning? Evaluating the Pitfalls of Noisy Methods Removing the influence of certain training data points from trained models ("unlearning") is a critical need driven by data privacy regulations. While a straightforward way to achieve this "exactly" i... 3.50 0% See Reviews View AI Dashboard
Layer-Based 3D Gaussian Splatting for Sparse-View CT Reconstruction We introduce a dynamic framework for 3D sparse-view Gaussian Splatting that learns scene representations through layerwise, iterative refinement of the Gaussian primitives. Conventional methods typica... 5.50 5% See Reviews View AI Dashboard
On the Existence of Universal Simulators of Attention Previous work on the learnability of transformers — focused on examining their ability to approximate specific algorithmic patterns through training — has largely been data-driven, offering only proba... 2.50 0% See Reviews View AI Dashboard
MotifScreen: Generalizing Virtual Screening through Learning Protein-Ligand Interaction Principles Virtual screening methods continue to face a fundamental trade-off between accuracy and efficiency. Deep learning-based methods attempting to address this challenge suffer from overfitting due to spar... 2.50 11% See Reviews View AI Dashboard
Diffusion Alignment as Variataional Expectation-Maximization Diffusion alignment aims to optimize diffusion models for the downstream objective. While existing methods based on reinforcement learning or direct backpropagation achieve considerable success in max... 6.00 0% See Reviews View AI Dashboard
A theory of parameter identifiability in data-constrained recurrent neural networks An increasingly common approach in neuroscience seeks to understand the brain by training recurrent neural networks (RNNs) to reproduce observed neural activity. Unlike brains, these RNNs can be compu... 3.50 0% See Reviews View AI Dashboard
Identifying Truthful Inheritance in Family Models and Enhancing Truthfulness Recent advances in large language models (LLMs) have led to emergence of specialized multimodal LLMs (MLLMs), creating distinct model families that share a common foundation language models. This wor... 3.33 24% See Reviews View AI Dashboard
Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models Large language models (LLMs) excel at complex reasoning but can still exhibit harmful behaviors. Current alignment strategies typically embed safety into model weights, making these controls implicit,... 4.00 58% See Reviews View AI Dashboard
EXPLOR: Extrapolatory Pseudo-Label Matching for OOD Uncertainty Based Rejection EXPLOR is a novel framework that utilizes support-expanding, extrapolatory pseudo-labeling to improve prediction and uncertainty-based rejection on out-of-distribution (OOD) points. EXPLOR utilizes a ... 4.67 0% See Reviews View AI Dashboard
Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents Large language model-based agents show promise for software engineering, but environment configuration remains a bottleneck due to heavy manual effort and scarce large-scale, high-quality datasets. Ex... 5.50 0% See Reviews View AI Dashboard
Pre-training under infinite compute Since compute grows much faster than web text available for language model pre-training, we ask how one should approach pre-training under fixed data and no compute constraints. We first show that exi... 7.50 0% See Reviews View AI Dashboard
DLGNet: Hyperedge Classification via a Directed Line Graph for Chemical Reactions Graphs and hypergraphs provide powerful abstractions for modeling interactions among a set of entities of interest and have been attracting a growing interest in the literature thanks to many successf... 4.67 0% See Reviews View AI Dashboard
Non-Additive Time-Series Forecasting via Cross-Decomposition and Linear Attention Many multivariate forecasters model additive effects well but miss non-additive interactions among temporal bases, variables, and exogenous drivers, which harms long-horizon accuracy and attribution. ... 3.50 41% See Reviews View AI Dashboard
ExploraQA: Embodied Question Answering with Long-horizon Proactive Exploration Embodied Question Answering (EQA) is a critical task for developing embodied intelligence, requiring agents to autonomously explore environments and answer human questions through perception, navigati... 3.33 0% See Reviews View AI Dashboard
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation. However, the practical inference speed of open-sourced Diffusion LLMs often lags behin... 7.00 18% See Reviews View AI Dashboard
MARWA: Multi-agent retrieval-augmented framework for reliable bioinformatics workflow automation The rapid growth of multi-omics data has driven the expansion of bioinformatics analysis tools. Common bioinformatics tasks often rely on workflows, which link multiple tools into structured pipelines... 4.50 17% See Reviews View AI Dashboard
A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs A primary challenge in developing large language models (LLMs) is their onerous pre-training cost. This paper explores a promising paradigm to improve LLM pre-training efficiency and quality by levera... 4.50 0% See Reviews View AI Dashboard
RHGCL: Representation-Driven Hierarchical Graph Contrastive Learning for User-Item Recommendation Graph Contrastive Learning (GCL), which fuses graph neural networks with contrastive learning, has evolved as a pivotal tool in user-item recommendations. While promising, existing GCL methods often l... 4.67 0% See Reviews View AI Dashboard
Local-Curvature-Aware Knowledge Graph Embedding via Extended Ricci Flow Knowledge graph embedding (KGE) relies on the geometry of the embedding space to encode semantic and structural relations. Existing methods place all entities on one homogeneous manifold—Euclidean, sp... 3.33 43% See Reviews View AI Dashboard
Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization Recent AI regulations call for data that remain useful for innovation while resistant to misuse, balancing utility with protection at the model level. Existing approaches either perturb data to make i... 6.00 6% See Reviews View AI Dashboard
Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension Designing efficient optimizers for large language models (LLMs) with low-memory requirements and fast convergence is an important and challenging problem. This paper makes a step towards the systemati... 6.50 0% See Reviews View AI Dashboard
Integrating Solving Forward and Inverse Problems in PDEs with Flow-based Models Solving partial differential equations (PDEs) given input parameters (forward problem) and inferring unknown parameters from partially observed solutions (inverse problem) are two critical problems in... 3.00 28% See Reviews View AI Dashboard
The Unreasonable Effectiveness of Scaling Agents for Computer Use Computer-use agents (CUAs) hold promise for automating everyday digital tasks, but their unreliability and high variance hinder their application to long-horizon, complex tasks. We introduce Behavior ... 4.00 0% See Reviews View AI Dashboard
Enumerate-Conjecture-Prove: Formally Solving Answer-Construction Problems in Math Competitions Mathematical reasoning is central to artificial intelligence, with applications in education, code generation, and research-level mathematical discovery. Mathematical competitions highlight two proble... 3.50 7% See Reviews View AI Dashboard
LU-500: A Logo Benchmark for Concept Unlearning Current concept unlearning approaches for copyright have achieved notable progress in handling styles or portrait-like representations. However, the task of unlearning company logos remains largely un... 2.50 22% See Reviews View AI Dashboard
PreviousPage 1 of 390 (19490 total rows)Next