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
$DA^2$-VPR: Dynamic Architecture for Domain-Aware Visual Place Recognition Visual Place Recognition (VPR) systems struggle with training-to-test domain shifts caused by environmental changes such as lighting, weather, and seasonal variations. Existing methods rely on input-i... 3.50 62% See Reviews View AI Dashboard
Fed-Duet: Dual Expert-Orchestrated Framework for Continual Federated Vision-Language Learning Pretrained vision-language models (VLMs), such as CLIP, have shown promise in federated learning (FL) by bringing strong multimodal representations to edge devices. However, continual adaptation remai... 5.00 38% See Reviews View AI Dashboard
On the (In)Significance of Feature Selection in High-Dimensional Datasets Feature selection (FS) is assumed to improve predictive performance and highlight meaningful features. We systematically evaluate this across $30$ diverse datasets, including RNA-Seq, mass spectrometr... 4.67 10% See Reviews View AI Dashboard
PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression Shapley values have emerged as a central game-theoretic tool in explainable AI (XAI). However, computing Shapley values exactly requires $2^d$ game evaluations for a model with $d$ features. Lundberg ... 4.50 0% See Reviews View AI Dashboard
Towards Human-Like Event Boundary Detection in Unstructured Videos through Scene-Action Transition Event segmentation research in psychology shows that humans naturally parse continuous activity into meaningful episodes by detecting boundaries marked by changes in perceptual features (e.g., motion)... 4.40 75% See Reviews View AI Dashboard
Usage-Aware Sentiment Representations in Large Language Models Large language models (LLMs) can encode high-level concepts as linear directions in their representation space, and sentiment has been studied in this framework. However, probe-derived sentiment direc... 4.00 36% See Reviews View AI Dashboard
AC-ODM: Actor–Critic Online Data Mixing for Sample-Efficient LLM Pretraining Pretraining data coverage and composition strongly influence the generalization of large language models (LLMs). While recent data-mixing approaches transfer domain weights learned by a small proxy mo... 4.00 0% See Reviews View AI Dashboard
Training-Free Watermarking for Autoregressive Image Generation Invisible image watermarking can protect image ownership and prevent malicious misuse of visual generative models. However, existing generative watermarking methods are mainly designed for diffusion m... 4.50 0% See Reviews View AI Dashboard
Token-Level Guided Discrete Diffusion for Membrane Protein Design Reparameterized diffusion models (RDMs) have recently matched autoregressive methods in protein generation, motivating their use for challenging tasks such as designing membrane proteins, which posses... 3.50 0% See Reviews View AI Dashboard
SymLight: Exploring Interpretable and Deployable Symbolic Policies for Traffic Signal Control Deep Reinforcement Learning have achieved significant success in automatically devising effective traffic signal control (TSC) policies. Neural policies, however, tend to be over-parameterized and non... 5.50 0% See Reviews View AI Dashboard
Beyond Raw Detection Scores: Markov-Informed Calibration for Boosting Machine-Generated Text Detection While machine-generated texts (MGTs) offer great convenience, they also pose risks such as disinformation and phishing, highlighting the need for reliable detection. Metric-based methods, which extrac... 4.50 0% See Reviews View AI Dashboard
Diff-Fair: Mitigating Intersectional Bias Through Diffusion-Driven Fair Representation Algorithmic fairness remains a critical challenge in Artificial-Intelligence, particularly for high-stakes domains where biased predictions can have significant societal consequences. While recent adv... 3.00 47% See Reviews View AI Dashboard
MARS: Optimizing Dual-System Deep Research via Multi-Agent Reinforcement Learning Large Reasoning Models (LRMs) often exhibit a tendency for overanalysis in simple tasks, where the models excessively utilize System 2-type, deliberate reasoning, leading to inefficient token generati... 3.50 46% See Reviews View AI Dashboard
Learnable Fractional Fourier and Graph Fractional Operators for Nonstationary Graph Signals Validated with EEG Seizure Detection Nonstationary graph signals with time-varying spectral properties and evolving network topologies present fundamental challenges for existing deep learning architectures. We introduce learnable fracti... 2.00 44% See Reviews View AI Dashboard
GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing Editing images using natural language instructions has become a natural and expressive way to modify visual content; yet, evaluating the performance of such models remains challenging. Existing evalua... 4.00 12% See Reviews View AI Dashboard
Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs Machine learning models trained on real-world data often inherit and amplify biases against certain social groups, raising urgent concerns about their deployment at scale. While numerous bias mitigati... 5.50 0% See Reviews View AI Dashboard
Forecasting-Conditioned Reinforcement Learning: Embedding Forecastability as an Inductive Bias We introduce Forecasting-Conditioned Reinforcement Learning (FoRL), an extension to model-free Reinforcement Learning (RL) agents that augments the policy with multi-step self-forecasts. FoRL is train... 4.00 37% See Reviews View AI Dashboard
The Art of Breaking Words: Rethinking Multilingual Tokenizer Design While model architecture and training objectives are well-studied, tokenization, particularly in multilingual contexts, remains a relatively neglected aspect of Large Language Model (LLM) development.... 2.50 15% See Reviews View AI Dashboard
Graph-Theoretic Intrinsic Reward: Guiding RL with Effective Resistance Exploration of dynamic environments with sparse rewards is a significant challenge in Reinforcement Learning, often leading to inefficient exploration and brittle policies. To address this, we introdu... 4.67 0% See Reviews View AI Dashboard
Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM Reasoning While Chain-of-Thought (CoT) prompting enhances the reasoning capabilities of large language models, the faithfulness of the generated rationales remains a critical open problem. We propose a novel th... 2.00 64% See Reviews View AI Dashboard
Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired approaches, such as Lla... 6.50 39% See Reviews View AI Dashboard
Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models Foundation models for natural language processing have many coherent definitions of hallucination and methods for its detection and mitigation. However, analogous definitions and methods do not exist ... 3.33 0% See Reviews View AI Dashboard
Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models The security issue of large language models (LLMs) has gained wide attention recently, with various defense mechanisms developed to prevent harmful output, among which safeguards based on text embeddi... 4.67 0% See Reviews View AI Dashboard
Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs Rotary Position Embeddings (RoPE) have become a standard for encoding sequence order in Large Language Models (LLMs) by applying rotations to query and key vectors in the complex plane. Standard imple... 6.00 2% See Reviews View AI Dashboard
Scaling Laws for Parameter Pruning in LLMs Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly growing memory and compute requirements, which makes dep... 2.50 25% See Reviews View AI Dashboard
Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique Growing concerns over the theft and misuse of Large Language Models (LLMs) underscore the need for effective fingerprinting to link a model to its original version and detect misuse. We define five es... 5.33 19% See Reviews View AI Dashboard
Focused Diffusion GAN: Object-Centric Image Generation Using Integrated GAN and Diffusion Frameworks Generative Adversarial Networks (GANs) and Diffusion Models (DMs) have shown significant progress in synthesizing high-quality object-centric images. However, generating realistic object-centric image... 3.00 77% See Reviews View AI Dashboard
Long Chain-of-Thought Reasoning Across Languages While large reasoning models have shown remarkable ability to generate long chains-of-thought (CoT) in English, we still lack understanding of how these long-form reasoning abilities transfer to the v... 5.50 0% See Reviews View AI Dashboard
PaT: Planning-after-Trial for Efficient Code Generation Large language models (LLMs) have demonstrated increasingly sophisticated capabilities for code generation. To extend the problem-solving reach of cost-efficient models to complex problems, strategic ... 3.50 3% See Reviews View AI Dashboard
Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models Vision-Language Models (VLMs) in remote sensing often fail at complex analytical tasks, a limitation stemming from their end-to-end training paradigm that bypasses crucial reasoning steps and leads to... 5.00 26% See Reviews View AI Dashboard
Exploring Non-linearity in Attention The representational ability of Transformer architectures arises from two sources of non-linearity: position-wise non-linearity via feed-forward layers and contextual non-linearity through self-attent... 3.00 0% See Reviews View AI Dashboard
UNDERSTANDING TRANSFORMERS FOR TIME SEIRES FORECASTING: A CASE STUDY ON MOIRAI We give a comprehensive theoretical analysis of transformers as time series pre- diction models, with a focus on MOIRAI (Woo et al., 2024). We study its ap- proximation and generalization capabilities... 5.33 0% See Reviews View AI Dashboard
Helmsman: Autonomous Synthesis of Federated Learning Systems via Multi-Agent Collaboration Federated Learning (FL) offers a powerful paradigm for training models on decentralized data, but its promise is often undermined by the immense complexity of designing and deploying robust systems. T... 4.00 84% See Reviews View AI Dashboard
MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrieval We introduce MRMR, the first expert-level multidisciplinary multimodal retrieval benchmark requiring intensive reasoning. MRMR contains 1,502 queries spanning 23 domains, with positive documents caref... 6.50 0% See Reviews View AI Dashboard
DUET: DISTILLED LLM UNLEARNING FROM AN EFFICIENTLY CONTEXTUALIZED TEACHER LLM unlearning is a technique to remove the impacts of undesirable knowledge from the model without retraining from scratch, which is indispensable towards trustworthy AI. Existing unlearning methods ... 5.00 0% See Reviews View AI Dashboard
Cost Volume Meets Prompt: Enhancing MVS with Prompts for Autonomous Driving Metric depth is foundational for perception, prediction, and planning in autonomous driving. Recent zero-shot metric depth foundation models still exhibit substantial distortions under large-scale ran... 4.00 23% See Reviews View AI Dashboard
BEEP3D: Box-Supervised End-to-End Pseudo-Mask Generation for 3D Instance Segmentation 3D instance segmentation is crucial for understanding complex 3D environments, yet fully supervised methods require dense point-level annotations, resulting in substantial annotation costs and labor o... 5.00 24% See Reviews View AI Dashboard
Bridging the Distribution Gap to Harness Pretrained Diffusion Priors for Super-Resolution Diffusion models, well recognized for their strong generative priors, have recently been increasingly applied to super-resolution (SR) tasks. However, as diffusion models are trained on Gaussian-corr... 5.00 0% See Reviews View AI Dashboard
Circuits, Features, and Heuristics in Molecular Transformers Transformers generate valid and diverse chemical structures, but little is known about the mechanisms that enable these models to understand the rules of molecular representation. We present a mechani... 5.00 65% See Reviews View AI Dashboard
MultiCrafter: High-Fidelity Multi-Subject Generation via Spatially Disentangled Attention and Identity-Aware Reinforcement Learning Multi-subject image generation aims to synthesize user-provided subjects in a single image while preserving subject fidelity, ensuring prompt consistency, and aligning with human aesthetic preferences... 4.50 9% See Reviews View AI Dashboard
DeepResearchGuard: Deep Research with Open Domain Evaluation and Multi-Stage Guardrails for Safety Current deep research frameworks lack adequate evaluation procedures and stage-specific safeguards. Prior work primarily treats evaluation as question-answering accuracy. It overlooks report quality, ... 4.00 0% See Reviews View AI Dashboard
AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the distillation of LLM-bas... 2.67 54% See Reviews View AI Dashboard
PitStop: Physics-Informed Training with Gradient Stopping Physics-informed learning offers a powerful approach for modeling physical systems by enforcing governing equations directly within the training process. However, optimizing such models remains inhere... 3.50 0% See Reviews View AI Dashboard
RDNAS: Robust Dual-Branch Neural Architecture Search Deep neural networks have achieved remarkable success but remain highly vulnerable to adversarial perturbations, posing serious challenges in safety-critical applications. We propose **RDNAS**, a robu... 4.00 51% See Reviews View AI Dashboard
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence Recent advances in depth-recurrent language models show that recurrence can decouple train-time compute and parameter count from test-time compute. In this work, we study how to convert existing pretr... 5.00 0% See Reviews View AI Dashboard
Adaptive Conformal Guidance for Learning under Uncertainty Learning with guidance has proven effective across a wide range of machine learning systems. Guidance may, for example, come from annotated datasets in supervised learning, pseudo-labels in semi-super... 6.50 15% See Reviews View AI Dashboard
Fragment-Wise Interpretability in Graph Neural Networks via Molecule Decomposition and Contribution Analysis Graph neural networks (GNNs) are widely used in the field of predicting molecular properties. However, their black box nature limits their use in critical areas like drug discovery. Moreover, existing... 3.20 7% See Reviews View AI Dashboard
Exposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors Multimodal large language models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet they remain highly susceptible to hallucinations, producing content that is fluent b... 4.00 0% See Reviews View AI Dashboard
Multimodal Few-Shot Point Cloud Segmentation via Agent Adaptation and Discriminative Deconfusion Few-shot 3D point cloud segmentation (FS-PCS) aims to leverage a limited amount of annotated data to enable the segmentation of novel categories. Most existing studies rely on single-modal point cloud... 4.50 0% See Reviews View AI Dashboard
STARTrack:Learning Spatio-Temporal Representation Evolution for Target-Aware Tracking Efficient modeling of spatio-temporal representations in videos is crucial for achieving accurate object tracking. Existing popular one-stream tracking frameworks typically introduce memory mechanisms... 4.50 0% See Reviews View AI Dashboard
PreviousPage 18 of 390 (19490 total rows)Next