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
Benchmarking Open-Set Recognition Beyond Vision-Language Pre-training Vision-language models (VLMs) with open-vocabulary pre-training can still fail in classification tasks, especially when the granularity of downstream labels misaligns with the supervision during pre-t... 5.50 5% See Reviews View AI Dashboard
Rep3D: Re-parameterize Large 3D Kernels with Low-Rank Receptive Modeling for Medical Imaging In contrast to vision transformers, which model long-range dependencies through global self-attention, large kernel convolutions provide a more efficient and scalable alternative, particularly in high... 4.00 37% See Reviews View AI Dashboard
Brain-Informed Language Model Training Enables Scalable and Generalizable Alignment with Human Brain Activity Language models (LMs) provide rich representational spaces that partially align with neural activity during naturalistic experiences such as movie watching. Yet leveraging brain recordings to actively... 3.00 22% See Reviews View AI Dashboard
Privacy \textit{Déjà Vu} Effect: Resurfacing Sensitive Samples in Continual Fine-tuning Continual fine-tuning of large pre-trained models is now ubiquitous in industry for adapting a model to freshly collected user data. Existing privacy protection practices assume earlier training data ... 5.00 0% See Reviews View AI Dashboard
DRDFL: Divide-and-conquer Collaboration for Efficient Ring-topology Decentralized Federated Learning Federated learning traditionally relies on server-based architecture, which often incur high communication costs and suffer from single points of failure. To avoid these limitations, we explore Ring-t... 4.50 11% See Reviews View AI Dashboard
DyBraSS: Dynamic Brain State Modeling with State-Space Model Brain states, observable through resting-state functional magnetic resonance imaging (rs-fMRI), represent dynamic transitions between recurring connectivity patterns and are closely linked to neurolog... 3.50 26% See Reviews View AI Dashboard
Better STEP, a format and dataset for boundary representation Boundary representation (B-rep) serves as the primary format for 3D geometry in computer-aided design (CAD), integrating parametric geometry with explicit topology to model complex components and asse... 3.50 0% See Reviews View AI Dashboard
AsseslyAI: AI–Powered Assessment Framework for Skill-Oriented Engineering Lab Education Practical lab education in computer science often faces challenges like plagiarism, lack of proper lab records, inadequate execution and assessment, limited student engagement, and absence of progress... 0.50 55% See Reviews View AI Dashboard
Q-learning Penalized Transformer for Safe Offline Reinforcement Learning This paper addresses the problem of safe offline reinforcement learning, which involves training a policy to satisfy safety constraints using an offline dataset. This problem is inherently challenging... 3.50 7% See Reviews View AI Dashboard
MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstruction 3D Gaussian Splatting (3DGS) has recently emerged as a powerful approach for high-quality dense surface reconstruction of unknown scenes. However, existing methods are limited by the assumption of sta... 4.00 9% See Reviews View AI Dashboard
Better LMO-based Momentum Methods with Second-Order Information The use of momentum in stochastic optimization algorithms has shown empirical success across a range of machine learning tasks. Recently, a new class of momentum-based stochastic algorithms has emerg... 6.00 0% See Reviews View AI Dashboard
FoundationMotion: Auto-labeling and Reasoning about Spatial Movement in Videos Motion understanding is fundamental to physical reasoning, enabling models to infer dynamics and predict future states. However, state-of-the-art models still struggle on recent motion benchmarks, pri... 3.50 20% See Reviews View AI Dashboard
ChainGeo: Enabling Effective Geometric Reasoning in Small VLMs through Interleaved Visual-Text Chains Solving geometric problems requires linking visual perception with symbolic reasoning. However, small Vision-Language Models (VLMs) often fail to keep this connection. We introduce ChainGeo, a novel f... 3.00 90% See Reviews View AI Dashboard
BrainPro: Towards Large-scale Brain State-aware EEG Representation Learning Electroencephalography (EEG) is a non-invasive technique for recording brain electrical activity, widely used in brain-computer interface (BCI) and healthcare. Recent EEG foundation models trained on ... 3.00 28% See Reviews View AI Dashboard
Generative Point Tracking with Flow Matching Tracking a point through a video can be a challenging task due to uncertainty arising from visual obfuscations, such as appearance changes and occlusions. Although current state-of-the-art discriminat... 4.00 0% See Reviews View AI Dashboard
Whitened Self-Attention Self-attention in Transformer architectures is formulated as a function of the pairwise contributions between target vectors and their context vectors. This con- struction implicitly assumes ternary a... 3.50 0% See Reviews View AI Dashboard
EHR2Path: Scalable Modeling of Longitudinal Health Trajectories with LLMs Healthcare systems face significant challenges in managing and interpreting vast, heterogeneous patient data for personalized care. Existing approaches often focus on narrow use cases with a limited f... 4.50 0% See Reviews View AI Dashboard
ConfRAG: Confidence-Guided Retrieval-Augmenting Generation Can Large Language Models (LLMs) be trained to avoid hallucinating factual statements, and can Retrieval-Augmented Generation (RAG) be triggered only when necessary to reduce retrieval and computation... 3.00 0% See Reviews View AI Dashboard
Visual Sparse Steering (VS2): Unsupervised Adaptation for Image Classification via Sparsity-Guided Steering Vectors Steering vision foundation models at test time, without retraining or access to large labeled datasets, is a desirable yet challenging goal, particularly in dynamic or resource-constrained settings. W... 4.50 10% See Reviews View AI Dashboard
AICrypto: A Comprehensive Benchmark for Evaluating Cryptography Capabilities of Large Language Models Large language models (LLMs) have demonstrated remarkable capabilities across a variety of domains. However, their applications in cryptography, which serves as a foundational pillar of cybersecurity,... 4.00 0% See Reviews View AI Dashboard
Advancing Multimodal Fusion on Heterogeneous Data with Physics-inspired Attention Multimodal fusion learning paradigm has shown great potential in various fields such as Medicine, Science, Engineering, etc. as it offers a framework to jointly learn from heterogeneous data sources. ... 3.33 0% See Reviews View AI Dashboard
The Illusion of Certainty: Uncertainty quantification for LLMs fails under ambiguity Accurate uncertainty quantification (UQ) in Large Language Models (LLMs) is critical for trustworthy deployment. While real-world language is inherently am- biguous, existing UQ methods are typically ... 4.67 0% See Reviews View AI Dashboard
Sparse-Smooth Decomposition for Nonlinear Industrial Time Series Forecasting Industrial time series forecasting faces unique challenges: hundreds of correlated sensors, complex nonlinear dynamics, and the critical need for interpretable models that engineers can trust. We intr... 2.50 100% See Reviews View AI Dashboard
EmoDialogCN: A Multimodal Mandarin Dyadic Dialogue Dataset of Emotions Face-to-face audiovisual interaction is fundamental to human communication, conveying rich and spontaneous emotional expressions. However, existing multimodal dialogue datasets suffer from irregular f... 3.33 22% See Reviews View AI Dashboard
Yet Another Scaling Axis with Some Free Lunch: Enlarging Token-indexed Parameters The scaling laws of large language models have driven remarkable progress, yet they reveal a fundamental bottleneck: performance gains from adding parameters diminish while computational costs grow ne... 4.50 43% See Reviews View AI Dashboard
SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs We present SpinBench, a cognitively grounded diagnostic benchmark for evaluating spatial reasoning in vision language models (VLMs). SpinBench is designed around the core challenge of spatial reasoni... 5.60 42% See Reviews View AI Dashboard
2D Quantization for Ultra‑low‑bit Optimizers Optimizer states used to accelerate neural network training become a significant memory bottleneck as model size grows. A common mitigation is to compress these high-precision states to low-bit repres... 4.00 0% See Reviews View AI Dashboard
CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering Medical question answering (QA) benchmarks often focus on multiple-choice or fact-based tasks, leaving open-ended answers to real patient questions underexplored. This gap is particularly critical in ... 6.67 14% See Reviews View AI Dashboard
Supervised Fine-Tuning on Ambiguous Preference Pairs Boosts LLM Alignment Preference learning constitutes a fundamental component in aligning large language models (LLMs) with human values and ethical expectations, where the quality of preference data plays a critical role.... 2.50 4% See Reviews View AI Dashboard
SeMa3D: Lifting Vision-Language Models for Unsupervised 3D Semantic Correspondence We tackle unsupervised dense semantic correspondence for 3D shapes, focusing on severe \textbf{non-isometric} deformations and \textbf{inter-class} matching--a regime where conventional functional map... 5.50 0% See Reviews View AI Dashboard
Leveraging Label Dependencies for Calibration in Multi-Label Classification through Proper Scoring Rule Modern Deep Neural Networks(DNNs) trained by using cross entropy for binary or multi-class classification are known to produce poorly calibrated probability estimates. While various calibration method... 3.00 0% See Reviews View AI Dashboard
Zooming into Comics: Region-Aware RL Improves Fine-Grained Comic Understanding in Vision-Language Models Complex visual narratives, such as comics, present a significant challenge to Vision-Language Models (VLMs). Despite excelling on natural images, VLMs often struggle with stylized line art, onomatopoe... 4.00 0% See Reviews View AI Dashboard
Confident and Adaptive Generative Speech Recognition via Conformal Risk Control Automatic Speech Recognition (ASR) systems frequently produce transcription errors due to acoustic variability, which require post-processing correction methods. Recent approaches leverage Large Langu... 4.67 69% See Reviews View AI Dashboard
Efficient Generative Models Personalization via Optimal Experimental Design Preference learning from human feedback has the ability to align generative models with the needs of end-users. Human feedback is costly and time-consuming to obtain, which creates demand for data-eff... 5.00 4% See Reviews View AI Dashboard
Self-Attention-Guided Genetic Programming: Leveraging BERT for Enhanced Tree-Structured Data Operations This study investigates the application of BERT to tree-structured data which presents a significant challenge due to its lack of explicit sequential order and complex topological dependencies. While ... 2.50 6% See Reviews View AI Dashboard
Meta-Optimizing ML Model Training A major challenge in training large-scale machine learning models is configuring the training process to maximize model performance, i.e., finding the best training setup from a vast design space. In ... 2.67 0% See Reviews View AI Dashboard
DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving Recent advances towards End-to-End Autonomous Driving (E2E-AD) focus on integrating modular designs into a unified framework for joint optimization. Most of these advances follow a sequential paradigm... 6.00 0% See Reviews View AI Dashboard
LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora Retrieval-Augmented Generation (RAG) is widely used to mitigate hallucinations of Large Language Models (LLMs) by leveraging external knowledge. While effective for simple queries, traditional RAG sys... 6.00 18% See Reviews View AI Dashboard
Do We Really Need Permutations? Impact of Width Expansion on Linear Mode Connectivity Recently, Ainsworth et al. empirically demonstrated that, given two independently trained models, applying a parameter permutation that preserves the input–output behavior allows the two models to be ... 5.00 10% See Reviews View AI Dashboard
DIVER : Large Language Model Decoding with Span-Level Mutual Information Verification Large language models (LLMs) have shown impressive capabilities in adapting to various tasks when provided with task-specific instructions. However, LLMs using standard decoding strategies often strug... 3.33 0% See Reviews View AI Dashboard
GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models In recent years, 2D Vision-Language Models (VLMs) have made significant strides in image-text understanding tasks. However, their performance in 3D spatial comprehension, which is critical for embodie... 5.00 9% See Reviews View AI Dashboard
IAgent: A Web Search Framework for Noise Isolation and Extended Information Access Web search agent frameworks built on Large Language Models (LLMs) can leverage multi-source, real-time external information, demonstrating strong potential. However, for deep research tasks that requi... 3.50 4% See Reviews View AI Dashboard
Convergence Theory of Decentralized Diffusion Models via Pseudo-Non-Markov Analysis Diffusion probabilistic models (DPMs) have demonstrated remarkable success in generative tasks, supported by a solid foundation of convergence analysis. Recently, decentralized DPMs have been propo... 5.50 0% See Reviews View AI Dashboard
MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning We present MA-RAG, a Multi-Agent framework for Retrieval-Augmented Generation (RAG) that addresses the inherent ambiguities and reasoning challenges in complex information-seeking tasks. Unlike conven... 3.00 64% See Reviews View AI Dashboard
Robust Mixture Models for Algorithmic Fairness Under Latent Heterogeneity Standard machine learning models optimized for average performance often fail on minority subgroups and lack robustness to distribution shifts. This challenge worsens when subgroups are latent and aff... 4.00 48% See Reviews View AI Dashboard
PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks, yet they still struggle to reliably verify the correctness of their own outputs. Existing solutions t... 5.50 26% See Reviews View AI Dashboard
From Single to Dual Reference: Reinforcement-Aligned Multi-Image Instruction-Guided Editing Most instruction-guided image editing models assume a single reference image. However, many real-world tasks—such as combining people into a group portrait, integrating a subject into a scene, or tran... 2.50 24% See Reviews View AI Dashboard
Shepherd: Pattern-Guided Trajectory Selection for Coding Agents on SWE-Bench Despite major improvements in LLM coding agents, their performance on complex software engineering tasks is still limited—leading models to solve only about half of the software engineering tasks in b... 3.50 7% See Reviews View AI Dashboard
Be Affective, Not Just Cognitive - Towards Imparting Pertinent Empathy in Dialogue Agents Empathetic Response Generation (ERG) has gained significant attention in diverse areas but still faces challenges that hinder its effectiveness. These challenges include $1$) the lack of affective emp... 4.67 N/A See Reviews
Layer-wise dynamic rank for compressing large language models Large language models (LLMs) have rapidly scaled in size, bringing severe memory and computational challenges that hinder their deployment. Singular Value Decomposition (SVD)-based compression has eme... 4.00 5% See Reviews View AI Dashboard
PreviousPage 16 of 390 (19490 total rows)Next