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
HURST: Learning Heterogeneity-Adaptive Urban Foundation Models for Spatiotemporal Prediction via Self-Partitional Mixture-of-Spatial-Experts Urban foundation models (UFMs) are pre-trained spatiotemporal (ST) prediction models with the ability to generalize to different tasks. Such models have the potential to transform urban intelligence b... 4.50 0% See Reviews View AI Dashboard
Stable Preference Optimization: Learning preference is more important than imitation Direct Preference Optimization (DPO; \citet{rafailov2023direct}) is a widely used method for aligning large language models (LLMs) with human feedback. However, its objective often leads to reward hac... 2.50 50% See Reviews View AI Dashboard
Robust Latent Neural Operators through Augmented Sparse Observation Encoding Neural operator methods have achieved significant success in the efficient simulation and inverse problems of complex systems by learning a mapping between two infinite-dimensional Banach spaces. Howe... 5.00 0% See Reviews View AI Dashboard
Dyana: Benchmarking Dynamic Hand Intelligence Most existing hand grasping benchmarks focus on static objects, which fails to capture the challenges of dynamic, real-world scenarios where targets move and precise timing becomes critical. We first ... 3.50 19% See Reviews View AI Dashboard
cgDDI: Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification Skin diseases impact the lives of millions of people around the world from different backgrounds and ethnicities. Therefore, accurate diagnosis in the dermatological domain requires focused work towar... 4.67 0% See Reviews View AI Dashboard
Adaptive Logit Adjustment for Debiasing Multimodal Language Models Vision-Language Models (VLMs) and Large Multimodal Models (LMMs) have significantly advanced image-to-text generation tasks such as image captioning and visual question answering (VQA). However, thes... 5.33 14% See Reviews View AI Dashboard
Not Just a Flash in Time: Interpreting Long Event Streams through Language Event cameras operate asynchronously with microsecond-level temporal precision and generate sparse event streams, enabling low-latency visual perception under high dynamic range conditions. However, c... 4.00 5% See Reviews View AI Dashboard
Training Variable Long Sequences With Data-centric Parallel Training deep learning models on variable long sequences poses significant computational challenges. Existing methods force a difficult trade-off between efficiency and ease-of-use. Simple approaches ... 4.00 4% See Reviews View AI Dashboard
Physics-informed Residual Flows Physics-Informed Neural Networks (PINNs) embed physical laws into deep learning models. However, conventional PINNs often suffer from failure modes leading to inaccurate solutions. We trace these fail... 5.00 47% See Reviews View AI Dashboard
Randomness Helps Rigor: A Probabilistic Learning Rate Scheduler Bridging Theory and Deep Learning Practice Learning rate schedulers have shown great success in speeding up the convergence of learning algorithms in practice. However, their convergence to a minimum has not been theoretically proven. This dif... 3.60 0% See Reviews View AI Dashboard
GeoFunFlow: Geometric Function Flow Matching for Inverse Operator Learning over Complex Geometries Inverse problems governed by partial differential equations (PDEs) are crucial in science and engineering. They are particularly challenging due to ill-posedness, data sparsity, and the added complexi... 4.00 39% See Reviews View AI Dashboard
Resolving Extreme Data Scarcity by Explicit Physics Integration: An Application to Groundwater Heat Transport Machine learning methods often struggle with real-world applications in science and engineering due to an insufficient amount or quality of training data. In this work, the example of subsurface porou... 3.00 0% See Reviews View AI Dashboard
OptimSyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation Large language models (LLMs) achieve strong downstream performance largely due to abundant supervised fine-tuning (SFT) data that imparts problem-solving capabilities. However, as applications expand,... 5.00 21% See Reviews View AI Dashboard
How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability Semantic associations such as the link between "bird" and "flew" are foundational for language modeling as they enable models to go beyond memorization and instead generalize and generate coherent tex... 7.20 0% See Reviews View AI Dashboard
PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning Robotic imitation learning typically requires models that capture multimodal action distributions while operating in real-time control rates and accommodating multiple sensing modalities. Although rec... 4.00 18% See Reviews View AI Dashboard
LLMs as Rules Oracles: Exploring Real-World Multimodal Reasoning in Tabletop Strategy Game Environments We introduce **LudoBench**, a multimodal reasoning benchmark that evaluates whether vision-enabled large language models (LMs) can acquire, integrate, and reason over heterogeneous game knowledge in m... 4.67 0% See Reviews View AI Dashboard
LLM Probability Concentration: How Alignment Shrinks the Generative Horizon Despite their impressive capabilities, aligned large language models (LLMs) often generate outputs that lack diversity. What drives this stability in the generation? We investigate this phenomenon thr... 3.60 9% See Reviews View AI Dashboard
From movement to cognitive maps: recurrent neural networks reveal how locomotor development shapes hippocampal spatial coding The hippocampus contains neurons whose firing correlates with an animal's location and orientation in space. Collectively, these neurons are held to support a cognitive map of the environment, enablin... 6.50 10% See Reviews View AI Dashboard
Learning Semantics, Not Addresses: Runtime Neural Prefetching for Far Memory Memory prefetching has long boosted CPU caches and is increasingly vital for far-memory systems, where large portions of memory are offloaded to cheaper, remote tiers. While effective prefetching requ... 3.00 0% See Reviews View AI Dashboard
Hierarchical Contrastive Reinforcement Learning: learn representation more suitable for RL environments Goal-conditioned reinforcement learning holds significant importance for real-world environment, but its inherent sparse reward structure brings challenges. In recent years, some researchers have atte... 3.00 0% See Reviews View AI Dashboard
CoIn: Coverage and Informativeness-Guided Token Reduction for Efficient Large Multimodal Models Large Multimodal Models (LMMs) have shown remarkable success in image understanding tasks. LMMs encode visual and textual inputs into tokens, which are then fed into Large Language Models (LLMs). Howe... 4.00 17% See Reviews View AI Dashboard
KV-Prune: Key–Value Similarity for Online Structured Pruning for Large Language Models Pruning has emerged as a promising direction for accelerating large language model (LLM) inference, yet existing approaches often suffer from instability because they rely on offline calibration data ... 4.00 19% See Reviews View AI Dashboard
Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learning Goal-Conditioned Reinforcement Learning (GCRL) mitigates the difficulty of reward design by framing tasks as goal reaching rather than maximizing hand-crafted reward signals. In this setting, the opti... 6.00 3% See Reviews View AI Dashboard
Dynamic Relational Priming Improves Transformer in Multivariate Time Series Standard attention mechanisms in transformers employ static token representations that remain unchanged across all pair-wise computations in each layer. This limits their representational alignment wi... 4.67 0% See Reviews View AI Dashboard
LLMs Can Get "Brain Rot"! We propose and test the **LLM Brain Rot Hypothesis**: continual exposure to *junk web text* induces lasting cognitive decline in large language models (LLMs). To causally isolate data quality, we run ... 4.50 0% See Reviews View AI Dashboard
Latent Light Source Modeling for Scene Reconstruction under Dynamic Illumination Modeling scenes under unknown, varying single-point illumination is crucial for applications such as interactive relighting, augmented reality, and robotics. However, existing dynamic novel-view synth... 2.50 9% See Reviews View AI Dashboard
T-GINEE: A Tensor-Based Multi-Graph Representation Learning While traditional network analysis focuses on single-layer networks, real-world systems often exhibit multiple types of relationships simultaneously, forming multilayer networks. However, existing mul... 4.00 69% See Reviews View AI Dashboard
DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoning The ''thinking with images'' paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of-thought to image-interactive reasoning. By invoki... 4.00 0% See Reviews View AI Dashboard
Spherical Watermark: Encryption-Free, Lossless Watermarking for Diffusion Models Diffusion models have revolutionized image synthesis but raise concerns around content provenance and authenticity. Digital watermarking offers a means of tracing generated media, yet traditional sche... 7.50 3% See Reviews View AI Dashboard
LogicSR: A Unified Benchmark for Logical Discovery from Data Discovering underlying logical expressions from data is a critical task for interpretable AI and scientific discovery, yet it remains poorly served by existing research infrastructure. The field of Sy... 6.00 10% See Reviews View AI Dashboard
What Matters for Batch Online Reinforcement Learning in Robotics? The ability to learn from large batches of autonomously collected data for policy improvement---a paradigm we refer to as batch online reinforcement learning---holds the promise of enabling truly scal... 4.50 0% See Reviews View AI Dashboard
Explaining the Reasoning of Large Language Models Using Attribution Graphs Large language models (LLMs) exhibit remarkable capabilities, yet their reasoning remains opaque, raising safety and trust concerns. Attribution methods, which assign credit to input features, have pr... 4.00 0% See Reviews View AI Dashboard
SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression We introduce SIRI, **S**caling **I**terative **R**einforcement Learning with **I**nterleaved Compression, a simple yet effective RL approach for Large Reasoning Models (LRMs) that enables more efficie... 3.50 0% See Reviews View AI Dashboard
Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitatio... 6.00 0% See Reviews View AI Dashboard
Huxley-G\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine Recent studies operationalize self-improvement through coding agents that edit their own codebases, grow a tree of self-modifications through expansion strategies that favor higher software engineerin... 6.00 5% See Reviews View AI Dashboard
Matched-Pair Experimental Design with Active Learning Matched-pair experimental designs aim to detect treatment effects by pairing participants and comparing within-pair outcome differences. In many situations, the overall effect size across the entire p... 4.00 0% See Reviews View AI Dashboard
Accelerated Parallel Tempering via Neural Transports Markov Chain Monte Carlo (MCMC) algorithms are essential tools in computational statistics for sampling from unnormalised probability distributions, but can be fragile when targeting high-dimensional,... 4.00 0% See Reviews View AI Dashboard
LLMs Must Think Thrice to Solve Executable Counterfactuals Counterfactual reasoning, a hallmark of intelligence, consists of three steps: inferring latent variables from observations (abduction), constructing alternative situations (interventions), and predic... 6.00 0% See Reviews View AI Dashboard
Structural Prognostic Event Modeling for Multimodal Cancer Survival Analysis The integration of histology images and gene profiles has shown great promise for improving survival prediction in cancer. However, current approaches often struggle to model intra- and inter-modal in... 5.00 0% See Reviews View AI Dashboard
Test-Time Layer Recurrence Enables Ultra-Deep Thinking in LLMs Without Chain-of-Thought Transformers possess a \textbf{neural depth} of only $O(1)$, which restricts them to solving primarily \textbf{inductive} reasoning problems of bounded depth. In contrast, recurrent models allow the l... 2.50 66% See Reviews View AI Dashboard
HoP: Homeomorphic Polar Learning for Hard Constrained Optimization Constrained optimization demands highly efficient solvers, which promotes the development of learn-to-optimize (L2O) approaches. As a data-driven method, L2O leverages neural networks to efficiently p... 3.00 3% See Reviews View AI Dashboard
Accurate Estimation of Mutual Information in High Dimensional Data Mutual information (MI) is a fundamental measure of statistical dependence between two variables, yet accurate estimation from finite data remains notoriously difficult. No estimator is universally re... 3.00 0% See Reviews View AI Dashboard
PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLM Recent advances in 3D content generation have amplified demand for dynamic models that are both visually realistic and physically consistent. However, state-of-the-art video diffusion models frequentl... 4.00 47% See Reviews View AI Dashboard
Convergence and Connectivity: Asymptotic Dynamics of Multi-Agent Q-Learning in Random Networks Beyond specific settings, many multi-agent learning algorithms fail to converge to an equilibrium solution, instead displaying complex, non-stationary behaviours such as recurrent or chaotic orbits. I... 4.50 0% See Reviews View AI Dashboard
MMWebGen: Benchmarking Multimodal Webpage Generation Multimodal generative models have advanced text-to-image generation and image editing. Recent unified models (UMs) can even craft interleaved images and text. However, the capacity of such models to s... 3.50 0% See Reviews View AI Dashboard
Elucidating Guidance in Variance Exploding Diffusion Models: Fast Convergence and Better Diversity Recently, the conditional diffusion models have shown an impressive performance in many areas, such as text-to-image, 3D, and video. To achieve a better alignment with the given condition, guidance-ba... 4.50 0% See Reviews View AI Dashboard
Autoregressive Direct Preference Optimization Direct preference optimization (DPO) has emerged as a promising approach for aligning large language models (LLMs) with human preferences. However, the widespread reliance on the response-level Bradle... 4.00 0% See Reviews View AI Dashboard
Reward Shaping Control Variates for Off-Policy Evaluation Under Sparse Rewards Off-policy evaluation (OPE) is essential for deploying reinforcement learning in safety-critical settings, yet existing estimators such as importance sampling and doubly robust (DR) often exhibit proh... 4.00 26% See Reviews View AI Dashboard
Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization This paper introduces **Story-Iter**, a new training-free iterative paradigm to enhance long-story generation. Unlike existing methods that rely on fixed reference images to construct a complete story... 5.33 0% See Reviews View AI Dashboard
FAFO: Lossy KV Cache Compression for Lossless Inference Acceleration via Draftless Fumble Decoding Lossy KV cache compression is a well-explored subfield of machine learning efficiency, with improved latency being one of its major gains. However, lossy compression techniques can fumble from time to... 4.50 0% See Reviews View AI Dashboard
PreviousPage 5 of 390 (19490 total rows)Next