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
Enhancing Zero-Shot LLM Recommendations via Semantics and Collaborative Signals Large Language Models (LLMs) perform well on ranking small candidate sets but, without task-specific training, remain inferior to well-trained conventional recommender models (CRMs) and fine-tuned LLM... 3.00 51% See Reviews View AI Dashboard
Optimizing for Persuasion Improves LLM Generalization: Evidence from Quality-Diversity Evolution of Debate Strategies Large Language Models (LLMs) optimized to output truthful answers often overfit, producing brittle reasoning that fails to generalize. While persuasion-based optimization has shown promise in debate s... 3.50 18% See Reviews View AI Dashboard
Identification of Task Affinity for Multi-Task Learning based on Divergence of Task Data Multi-task learning (MTL) can significantly improve performance by training shared models for related tasks. However, due to the risk of negative transfer between mismatched tasks, the effectiveness o... 4.00 41% See Reviews View AI Dashboard
MetaRuleReasoner: Beyond Chain-of-Thought—Neural Rule-Based Reasoning for Reliable Mathematical Computation Chain-of-thought reasoning has emerged as the dominant paradigm for mathematical reasoning in large language models, yet it suffers from fundamental limitations: hallucination in reasoning steps, inco... 2.00 78% See Reviews View AI Dashboard
Fairness-Aware EHR Analysis via Structured Missing Pattern Modeling and Adversarial Low-Rank Adaptation Deep learning has been widely applied to electronic health record (EHR) analysis, offering strong predictive capabilities for clinical outcome prediction. However, due to inherent disparities across d... 3.00 82% See Reviews View AI Dashboard
Hierarchical Quantized Diffusion Based Tree Generation Method for Hierarchical Representation and Lineage Analysis In single-cell research, tracing and analyzing high-throughput single-cell differentiation trajectories is crucial for understanding complex biological processes. Key to this is the modeling and gener... 6.00 21% See Reviews View AI Dashboard
RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm Post-training Quantization (PTQ) has become a widely used technique for improving inference efficiency of large language models (LLMs). However, existing PTQ methods generally suffer from crucial limi... 2.67 0% See Reviews View AI Dashboard
CroCoDiLight: Repurposing Cross-View Completion Encoders for Relighting Cross-view completion (CroCo) has proven effective as pre-training for geometric downstream tasks such as stereo depth, optical flow, and point cloud prediction. In this paper we show that it also lea... 5.00 0% See Reviews View AI Dashboard
Learning from What the Model Forgets: Prototype-Guided Patch-wise Replay for Medical Image Segmentation Medical image segmentation remains a challenging problem due to the presence of hard positive samples that deviate from class centers and are frequently forgotten during training. These moderately for... 4.50 43% See Reviews View AI Dashboard
RefineBench: Evaluating Refinement Capability in Language Models Can language models (LMs) self-refine their own responses? This question is increasingly relevant as more than 10% of real-world user interactions involve refinement requests (see Appendix F). Yet pri... 5.50 0% See Reviews View AI Dashboard
Learning Generalized Hamiltonian Dynamics with Stability from Noisy Trajectory Data We propose a unified framework for learning generalized Hamiltonian dynamics from noisy, sparse phase-space observations via variational Bayesian inference. Modeling conservative, dissipative, and por... 3.00 5% See Reviews View AI Dashboard
Goal-driven Bayesian Optimal Experimental Design for Robust Decision-Making Under Model Uncertainty Bayesian optimal experimental design (BOED) aims to predict experiments that can optimally reduce the uncertainty in the model parameters. However, in many decision-critical applications, accurate par... 3.00 10% See Reviews View AI Dashboard
Time series saliency maps: Explaining models across multiple domains Traditional saliency map methods, popularized in computer vision, highlight individual points (pixels) of the input that contribute the most to the model's output. However, in time-series they offer l... 4.00 0% See Reviews View AI Dashboard
CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration Recent advancements in text-to-image synthesis have been largely propelled by diffusion-based models, yet achieving precise alignment between text prompts and generated images remains a persistent cha... 4.00 0% See Reviews View AI Dashboard
What happens when generative AI models train recursively on each others' outputs? The internet serves as a common source of training data for generative AI (genAI) models but is increasingly populated with AI-generated content. This duality raises the possibility that future genAI ... 5.00 0% See Reviews View AI Dashboard
Are complicated loss functions necessary for teaching LLMs to reason? Recent advances in large language models (LLMs) highlight the importance of post-training techniques for improving reasoning and mathematical ability. Group Relative Policy Optimization (GRPO) has sho... 2.00 21% See Reviews View AI Dashboard
Model-Agnostic Text Condensation with Coherence Awareness Data condensation has emerged as a promising technique for improving training efficiency. However, it remains challenging to produce a small synthetic text set that retains its utility for use with la... 4.00 0% See Reviews View AI Dashboard
Perishable Online Inventory Control with Context-Aware Demand Distributions We study the online contextual inventory control problem with perishable goods. In this work, we propose and consider a more realistic---and more challenging---setting where both the expected demand a... 4.40 0% See Reviews View AI Dashboard
Describe-to-Score: Text-Guided Efficient Image Complexity Assessment Accurately assessing image complexity (IC) is critical for computer vision, yet most existing methods rely solely on visual features and often neglect high-level semantic information, limiting their a... 4.50 5% See Reviews View AI Dashboard
UniFLoW: Universal Multi-Modal Federated LoRA Fine-Tuning Framework with Analytical Aggregation As Multimodal Large Language Models (MLLMs) continue to be trained, the availability of public data diminishes, limiting the possibility for further training and adaptation. However, private data rema... 4.00 2% See Reviews View AI Dashboard
Think First, Then Select and Verify with Query–Key Alignment We demonstrate that a “think-first” phase via chain-of-thought (CoT) prompting systematically strengthens internal query–key (QK) alignment improving ability to select and verify answers directly from... 2.00 0% See Reviews View AI Dashboard
Test-Time Accuracy-Cost Control in Neural Simulators via Recurrent-Depth Accuracy-cost trade-offs are a fundamental aspect of scientific computing. Classical numerical methods inherently offer such a trade-off: increasing resolution, order, or precision typically yields mo... 5.50 5% See Reviews View AI Dashboard
ClusCAM: Clustered Visual Explanations for Vision Models in Image Classification As deep neural networks continue to achieve considerable success in high-stakes computer vision applications, the demand for transparent and interpretable decision-making is becoming increasingly crit... 4.67 14% See Reviews View AI Dashboard
DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learning Deep graph models have achieved great success in network representation learning. However, their focus on pairwise relationships restricts their ability to learn pervasive higher-order interactions in... 5.50 0% See Reviews View AI Dashboard
SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network pruning offers a viable so... 4.00 0% See Reviews View AI Dashboard
Energy-Guided Prompt Optimization for Controllable Cross-Architectural Diffusion Models Diffusion-based generative methods have fundamentally reshaped the process of converting textual descriptions into visual representations. However, consistently enforcing semantic constraints across a... 3.00 100% See Reviews View AI Dashboard
FastFace: Training-Free Identity Preservation Tuning in Distilled Diffusion via Guidance and Attention The recent proliferation of identity-preserving (ID) adapters has significantly advanced personalized generation with diffusion models. However, these adapters are predominantly co-trained with base d... 4.00 4% See Reviews View AI Dashboard
Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers Text-to-video and image-to-video generation have made rapid progress in visual quality, but they remain limited in controlling the precise timing of motion. In contrast, audio provides temporal cues ... 4.50 6% See Reviews View AI Dashboard
DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL Augmenting large language models (LLMs) with browsing tools substantially improves their potential as deep search agents to solve complex, real-world tasks. Yet, open LLMs still perform poorly in such... 4.00 16% See Reviews View AI Dashboard
Towards Automatic Discovery and Explanation of Differences Between Vision Models Researchers and developers often compare state-of-the-art and newly developed models beyond benchmark scores, using techniques such as visualizations, case-by-case analyses, and qualitative evaluation... 2.50 0% See Reviews View AI Dashboard
One Measure, Many Bounds: Bridging TV, Variance, and Mutual Information Understanding the generalization of machine learning algorithms remains a fundamental challenge. While mutual information provides a powerful lens for analysis, we introduce a more flexible, one-param... 3.00 72% See Reviews View AI Dashboard
Mitigating Privacy Risk via Forget Set-Free Unlearning Training machine learning models requires the storage of large datasets, which often contain sensitive or private data. Storing data is associated with a number of potential risks which increase over ... 5.00 0% See Reviews View AI Dashboard
Global optimization of graph acquisition functions for neural architecture search Graph Bayesian optimization (BO) has shown potential as a powerful and data-efficient tool for neural architecture search (NAS). Most existing graph BO works focus on developing graph surrogate models... 4.67 0% See Reviews View AI Dashboard
Five-Mode Tucker-LoRA for Video Diffusion on Conv3D Backbones Parameter-efficient fine-tuning for text-to-video diffusion remains challenging. Most LoRA-style adapters either flatten 3D kernels into 2D matrices or add temporal-only modules, which breaks the nati... 2.50 39% See Reviews View AI Dashboard
Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models Large reasoning models (LRMs) exhibit unprecedented capabilities in solving complex problems through Chain-of-Thought (CoT) reasoning. However, recent studies reveal that their final answers often con... 4.50 6% See Reviews View AI Dashboard
Extending RLVR to Open-Ended Tasks via Verifiable Multiple-Choice Reformulation Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated great potential in enhancing the reasoning capabilities of large language models (LLMs), achieving remarkable progress in domains... 3.50 30% See Reviews View AI Dashboard
Real-time Echocardiography Video Segmentation via Slot Propagation, Spatiotemporal Feature Fusion, and Frequency-phase Enhancement Accurate and real-time segmentation of cardiac structures in echocardiography videos is crucial for the diagnosis and treatment of heart disease. However, it is a very challenging task due to low imag... 2.50 11% See Reviews View AI Dashboard
EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs Speech-to-speech large language models (SLLMs) are attracting increasing attention. Derived from text-based large language models (LLMs), SLLMs often exhibit degradation in knowledge and reasoning cap... 2.50 0% See Reviews View AI Dashboard
From Ambiguity to Verdict: A Semiotic‑Grounded Multi‑Perspective Agent for LLM Logical Reasoning Logical reasoning is a fundamental capability of large language models (LLMs). However, existing studies largely overlook the interplay between *logical complexity* and *semantic complexity*, resultin... 4.00 55% See Reviews View AI Dashboard
When Unlearning Backfires: Partial Unlearning Increases PII Regurgitation and enables data extraction in Meta’s Llama 3.2 1B We study partial unlearning—selectively removing only a subset of a knowledge source—and its safety side effects in LLaMA 3.2 1B. Using a targeted pipeline that unlearns the seven Harry Potter novels ... 2.50 4% See Reviews View AI Dashboard
ExpeSQL: An Experience-Guided Decompositional Search Framework for Text-to-SQL Large language models have advanced Text-to-SQL, yet enterprise deployment remains challenging due to complex, evolving schemas, domain shift, privacy constraints, and latency/cost budgets. We introdu... 4.00 34% See Reviews View AI Dashboard
The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies Large Language Models (LLMs) are increasingly used for social simulation, where populations of agents are expected to reproduce human-like collective behavior. However, we find that many recent studie... 4.00 11% See Reviews View AI Dashboard
Estimating structural shifts in graph domain adaptation via pairwise likelihood maximization Graph domain adaptation (GDA) emerges as an important problem in graph machine learning when the distribution of the source graph data used for training is different from that of the target graph data... 5.00 0% See Reviews View AI Dashboard
CoFact: Conformal Factuality Guarantees for Language Models under Distribution Shift Large Language Models (LLMs) excel in natural language processing (NLP) tasks but often generate false or misleading information, known as hallucinations, raising reliability concerns in high-stakes a... 5.50 22% See Reviews View AI Dashboard
NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models With the rapid adoption of diffusion models for visual content generation, proving authorship and protecting copyright have become critical. This challenge is particularly important when model owners ... 4.50 11% See Reviews View AI Dashboard
NeuMoSync: End‑to‑End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning Continual learning (CL) requires models to learn tasks sequentially, yet deep neural networks often suffer from plasticity loss and poor knowledge transfer, which can impede their long-term adaptabili... 5.50 8% See Reviews View AI Dashboard
Continuous multinomial logistic regression for neural decoding Multinomial logistic regression (MLR) is a classic model for multi-class classification that has been widely used for neural decoding. However, MLR requires a finite set of discrete output classes, li... 5.50 28% See Reviews View AI Dashboard
Language Models That Think, Chat Better Reinforcement learning with verifiable rewards (RLVR) improves language model reasoning by using rule-based rewards in verifiable domains such as mathematics and code. However, RLVR leads to limited g... 4.50 0% See Reviews View AI Dashboard
Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features Large language models exhibit emergent misalignment behaviors during test-time generation, necessitating dynamic control mechanisms for safe deployment. Inspired by sparse interpretable representation... 4.00 64% See Reviews View AI Dashboard
AlphaZeroES: Direct Score Maximization Can Outperform Planning Loss Minimization in Single-Agent Settings Planning at execution time has been shown to dramatically improve performance for AI agents. A well-known family of approaches to planning at execution time in single-agent settings and two-player zer... 3.00 0% See Reviews View AI Dashboard
PreviousPage 4 of 390 (19490 total rows)Next