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
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents Advances in Large Language Models (LLMs) have enabled a new class of \textbf{\textit{self-evolving agents}} that autonomously improve through interaction with the environment, demonstrating strong cap... 5.50 8% See Reviews View AI Dashboard
Ensemble Prediction of Task Affinity for Efficient Multi-Task Learning A fundamental problem in multi-task learning (MTL) is identifying groups of tasks that should be learned together. Since training MTL models for all possible combinations of tasks is prohibitively exp... 5.33 14% See Reviews View AI Dashboard
Bridging Unsupervised and Semi-Supervised Anomaly Detection: A Provable and Practical Framework with Synthetic Anomalies Anomaly detection (AD) is a critical task across domains such as cybersecurity and healthcare. In the unsupervised setting, an effective and theoretically-grounded principle is to train classifiers to... 3.33 0% See Reviews View AI Dashboard
How Does Fine-Tuned Foundation Models Help for Long-Tailed Data Deep long-tail learning is a challenging visual recognition problem that trains models on long-tailed distributed datasets. In the last decade, a large number of methods have been proposed to solve th... 4.50 0% See Reviews View AI Dashboard
How to Teach Label to Understand Decisions: A Decision-aware Label Distribution Learning Framework Contextual Stochastic Optimization (CSO) aims to predict uncertain, context-dependent parameters to inform downstream decisions. A central challenge is that high predictive accuracy does not necessari... 4.00 54% See Reviews View AI Dashboard
Online Test-Time Adaptation in Tabular Data with Minimal High-Certainty Samples Tabular data is ubiquitous across real-world applications. While self-supervised learning has advanced representation learning for tabular data, most methods assume the unrealistic IID setting. In pra... 2.00 8% See Reviews View AI Dashboard
Don't Trust any Distilled Dataset! Model Hijacking with the Fewest Samples Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources. Meanwhile, dataset distillation emerges to synthesize a com... 3.50 0% See Reviews View AI Dashboard
Trade-off in Estimating the Number of Byzantine Clients in Federated Learning Federated learning is very popular for large-scale optimization and machine learning, but is also vulnerable to Byzantine clients that can send any erroneous signals. Robust aggregators are commonly u... 4.67 0% See Reviews View AI Dashboard
Explicitly Bounding Q‑Function Estimates for Offline-to-Online Reinforcement Learning Offline-to-Online Reinforcement Learning (O2O RL) presents a compelling framework for deploying decision-making agents in domains where online data collection is limited by practical constraints such ... 3.50 32% See Reviews View AI Dashboard
TBG-Driven Minimization of Noise-Resistant Adaptive Sharpness Awareness Driven by the sharpness of the loss surface effectively indicate the generalization gap, sharpness-awareness minimization (SAM) aims at flat minima within the loss landscape. However, to protect sens... 2.00 10% See Reviews View AI Dashboard
DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools/resources for travel itinerary generation, ensuring enjoyable user experience. Despite its ... 4.50 0% See Reviews View AI Dashboard
Transferring Jailbreak Attacks from Public to Private LLMs via Local Prompt Optimization Large Language Models (LLMs) demonstrate remarkable capabilities across natural language processing tasks but remain vulnerable to jailbreak attacks, where adversarial inputs are crafted to elicit har... 3.50 9% See Reviews View AI Dashboard
MANGO: Natural Multi-speaker 3D Talking Head Generation via 2D-Lifted Enhancement Current audio-driven 3D head generation methods mainly focus on single-speaker scenarios, lacking natural, bidirectional listen-and-speak interaction. Achieving seamless conversational behavior, where... 4.50 0% See Reviews View AI Dashboard
Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation Diffusion models have achieved impressive results in generating high-quality images. Yet, they often struggle to faithfully align the generated images with the input prompts. This limitation arises fr... 4.67 0% See Reviews View AI Dashboard
PoseDiff: A Unified Diffusion Model Bridging Robot Pose Estimation and Video-to-Action Control We present PoseDiff, a conditional diffusion model that unifies robot state estimation and control within a single framework. At its core, PoseDiff maps raw visual observations into structured robot s... N/A 52% See Reviews View AI Dashboard
ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation Recent advancements in large reasoning models (LRMs) like DeepSeek-R1 and OpenAI o1 series have achieved notable performance enhancements on complex reasoning tasks by scaling up the generation length... 4.50 0% See Reviews View AI Dashboard
Einstein Fields: A Neural Perspective To Computational General Relativity We introduce Einstein Fields, a neural representation designed to compress computationally intensive four-dimensional numerical relativity simulations into compact implicit neural network weights. By ... 6.67 0% See Reviews View AI Dashboard
PRISM: Controllable Diffusion for Compound Image Restoration with Scientific Fidelity Scientific and environmental imagery are often degraded by multiple compounding factors related to sensor noise and environmental effects. Existing restoration methods typically treat these compound e... 4.00 48% See Reviews View AI Dashboard
Rethinking Scale: How Multi-Agent Collaboration Enables Smaller Models to Rival GPT-4 in Video Understanding The rapid development of large language models (LLMs) has brought new perspectives to the field of video understanding. However, existing methods often rely on large-scale proprietary models, such as ... 5.00 0% See Reviews View AI Dashboard
Achieving Noise Robustness by additive normalization of labels As machine learning models scale, the demand for large volumes of high-quality training data grows, but acquiring clean datasets is costly and time-consuming due to detailed human annotation and noisy... 3.60 15% See Reviews View AI Dashboard
Graph-Based Operator Learning from Limited Data on Irregular Domains Operator learning seeks to approximate mappings from input functions to output solutions, particularly in the context of partial differential equations (PDEs). While recent advances such as DeepONet a... 2.00 50% See Reviews View AI Dashboard
GDEGAN: Gaussian Dynamic Equivariant Graph Attention Network for Ligand Binding Site Prediction Accurate prediction of binding sites of a given protein, to which ligands can bind, is a critical step in structure-based computational drug discovery. Recently, Equivariant Graph Neural Networks (GN... 4.00 21% See Reviews View AI Dashboard
A State-Transition Framework for Efficient LLM Reasoning While Long Chain-of-Thought (CoT) reasoning significantly improves Large Language Models (LLMs) performance on complex reasoning tasks, the substantial computational and memory costs of generating lon... 5.50 0% See Reviews View AI Dashboard
Learning without Global Backpropagation via Synergistic Information Distillation Backpropagation (BP), while foundational to deep learning, imposes two critical scalability bottlenecks: update locking, where network modules remain idle until the entire backward pass completes, and... 3.50 75% See Reviews View AI Dashboard
SADA: Safe and Adaptive Inference with Multiple Black-Box Predictions Real-world applications often face scarce labeled data due to the high cost and time requirements of gold-standard experiments, whereas unlabeled data are typically abundant. With the growing adoption... 5.00 0% See Reviews View AI Dashboard
TRANSPORT-BASED MEAN FLOWS FOR GENERATIVE MODELING Flow-matching generative models have emerged as a powerful paradigm for continuous data generation, achieving state-of-the-art results across domains such as images, 3D shapes, and point clouds. Despi... 3.00 10% See Reviews View AI Dashboard
v-HUB: A Visual-Centric Humor Understanding Benchmark for Video LLMs AI models capable of comprehending humor hold real-world promise—for example, enhancing engagement in human-machine interactions. To gauge and diagnose the capacity of multimodal large language models... 3.50 0% See Reviews View AI Dashboard
BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving Diffusion-based planners have shown great promise for autonomous driving due to their ability to capture multi-modal driving behaviors. However, guiding these models effectively in reactive, closed-lo... 5.50 0% See Reviews View AI Dashboard
EduVerse: A User-Defined Multi-Agent Simulation Space for Education Scenario Reproducing cognitive development, group interaction, and long-term evolution in virtual classrooms remains a core challenge for educational AI, as real classrooms integrate open-ended cognition, dyna... 4.00 46% See Reviews View AI Dashboard
Parameter-Efficient Subspace Optimization for LLM Fine-Tuning This paper develops a new perspective on parameter-efficient training for LLMs, inspired by the classical theory of subspace minimization. We introduce a unifying framework, Parameter-Efficient Subspa... 3.00 7% See Reviews View AI Dashboard
Internalizing Self-Consistency in Language Models: Multi-Agent Consensus Alignment Language Models (LMs) are inconsistent reasoners, often generating contradictory responses to identical prompts. While inference-time methods can mitigate these inconsistencies, they fail to address t... 4.00 17% See Reviews View AI Dashboard
Boosting Federated Model Convergence with Anomaly Detection and Exclusion Federated Learning (FL) is becoming increasingly important in AI training, particularly for privacy-sensitive applications. At the same time, it has become a subject of malicious action and needs bett... 3.33 0% See Reviews View AI Dashboard
Duet: Joint Exploration of User–Item Profiles Traditional recommendation systems represent users and items as hidden vectors, learning to align them in a shared latent space for relevance estimation. With the advent of large language models (LLMs... 3.50 39% See Reviews View AI Dashboard
NoLoRA: Nonlinear Low-Rank Adaptation for Parameter-Efficient Fine-Tuning Low-Rank Adaptation (LoRA) has been widely adopted for parameter-efficient fine-tuning of large language models, as it enables effective adaptation while maintaining efficiency. However, existing LoRA... 2.00 41% See Reviews View AI Dashboard
NO DARK DATA REQUIRED: BRIDGING THE GAP BETWEEN NORMAL AND LOW-LIGHT DETECTION VIA RETINEX DECOMPOSITION Conventional low-light object detection approaches typically involve distinct image enhancement modules before the detection process. This can lead to compromised performance due to misaligned objecti... 2.00 87% See Reviews View AI Dashboard
Self-Improved Prior for All-in-One Image Restoration Unified image restoration models for diverse and mixed degradations often suffer from unstable optimization dynamics and inter-task conflicts. This paper introduces Self-Improved Privilege Learning (S... 4.67 34% See Reviews View AI Dashboard
LINGOLY-TOO: Disentangling Reasoning from Knowledge with Templatised Orthographic Obfuscation Frontier language models appear strong at solving reasoning problems, but their performance is often inflated by shortcuts such as memorisation and knowledge. We introduce LingOLY-TOO, a challenging r... 5.00 0% See Reviews View AI Dashboard
Finetuning-free Alignment of Diffusion Model for Text-to-Image Generation Diffusion models have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained diffusion models to maximize a given... 5.00 8% See Reviews View AI Dashboard
Group Pattern Selection Optimal: Let LRMs Pick the Right Pattern for Reasoning Large reasoning models (LRMs) exhibit diverse high-level reasoning patterns (e.g., direct solution, reflection-and-verification, and exploring multiple solutions), yet prevailing training recipes impl... 3.50 46% See Reviews View AI Dashboard
Learning Task-Invariant Features in VLMs via Dynamic Bayesian IRM While Visual Language Models (VLMs) excel on multimodal tasks, they suffer from performance degradation under distribution shift, particularly when facing out-of-distribution (OOD) tasks not seen duri... 2.50 94% See Reviews View AI Dashboard
Diffusion Aligned Embeddings This paper introduced DAE, which formulates dimensionality reduction as aligning diffusion processes between high- and low-dimensional spaces. By minimizing the Path-KL divergence—which uniquely captu... 2.80 36% See Reviews View AI Dashboard
Membrane Potential Perturbation Dynamic Is Total Variation Membrane potential perturbation dynamic (MPPD) is an emerging approach to capture perturbation intensity and stabilize the performance of spiking neural networks (SNN). It discards the neuronal reset ... 5.00 0% See Reviews View AI Dashboard
Exploiting Low-Dimensional Manifold of Features for Few-shot Whole Slide Image Classification Few-shot Whole Slide Image (WSI) classification is severely hampered by overfitting. We argue that this is not merely a data-scarcity issue but a fundamentally geometric problem. Grounded in the manif... 5.50 0% See Reviews View AI Dashboard
TeFlow: Enabling Multi-frame Supervision for Feed-forward Scene Flow Estimation Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusio... 4.67 8% See Reviews View AI Dashboard
KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual Animation Generating video from various conditions, such as text, image, and audio, enables precise spatial and temporal control, leading to high-quality generation results. Most existing audio-to-visual animat... 5.50 0% See Reviews View AI Dashboard
Mode-conditioning unlocks superior test-time compute scaling Parallel sampling promises substantial gains in test-time scaling, but its effectiveness is sharply limited by diversity collapse, where models concentrate on a few modes and repeated samples reproduc... 5.00 0% See Reviews View AI Dashboard
IMPQ: Interaction-Aware Layerwise Mixed Precision Quantization for LLMs Large Language Models (LLMs) promise impressive capabilities, yet their multi-billion-parameter scale makes on-device or low-resource deployment prohibitive. Mixed-precision quantization offers a comp... 4.50 68% See Reviews View AI Dashboard
HSIC Bottleneck for Cross-Generator and Domain-Incremental Synthetic Image Detection Synthetic image generators evolve rapidly, challenging detectors to generalize across current methods and adapt to new ones. We study domain-incremental synthetic image detection with a two-phase eval... 4.00 11% See Reviews View AI Dashboard
Transport Clustering: Solving Low-Rank Optimal Transport via Clustering Optimal transport (OT) finds a least cost transport plan between two probability distributions using a cost matrix over pairs of points. Constraining the rank of the transport plan yields low-rank OT,... 6.50 0% See Reviews View AI Dashboard
QORA: A Sustainable Framework for Open-World Generative Model Attribution with Quasi-Orthogonal Representation Disentanglement The rapid emergence of new generative models poses significant challenges to static attribution frameworks, which often confidently misattribute images from unknown sources to known ones and struggle ... 3.50 37% See Reviews View AI Dashboard
PreviousPage 9 of 390 (19490 total rows)Next