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
Deep Neural Networks Divide and Conquer Dihedral Multiplication We find multilayer perceptrons and transformers both learn an instantiation of the same divide-and-conquer algorithm and solve dihedral multiplication with logarithmic feature efficiency. Applying pri... 3.50 0% See Reviews View AI Dashboard
Is Extending Modality The Right Path Towards Omni-Modality? Omni-modal language models (OLMs) aim to integrate and reason over diverse input modalities—such as text, images, video, and audio—while maintaining strong language capabilities. Despite recent advanc... 3.50 0% See Reviews View AI Dashboard
Welfarist Formulations for Diverse Similarity Search Nearest Neighbor Search (NNS) is a fundamental problem in data structures with wide-ranging applications, such as web search, recommendation systems, and, more recently, retrieval-augmented generation... 6.50 0% See Reviews View AI Dashboard
Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures Large language models (LLMs) increasingly generate intermediate reasoning structures --- rubrics, checklists, proof graphs --- to make their decisions more interpretable. But are these structures caus... 4.50 24% See Reviews View AI Dashboard
Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining The task adaptation and alignment of Large Multimodal Models (LMMs) have been significantly advanced by instruction tuning and further strengthened by recent preference optimization. Yet, most LMMs st... 3.00 4% See Reviews View AI Dashboard
An Empirical Study and Theoretical Explanation on Task-Level Model-Merging Collapse Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we observe that merging ... 4.00 15% See Reviews View AI Dashboard
StoryAlign: Evaluating and Training Reward Models for Story Generation Story generation aims to automatically produce coherent, structured, and engaging narratives. Although large language models (LLMs) have significantly advanced text generation, stories generated by LL... 6.50 16% See Reviews View AI Dashboard
Logarithmic Regret in Preference Learning via Optimistic PAC-Bayesian Particle Ensembles The remarkable sample efficiency of preference-based reinforcement learning, which underpins the alignment of large language models with human feedback (RLHF), presents a significant theoretical puzzl... 4.00 65% See Reviews View AI Dashboard
The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimization The application of Reinforcement Learning with Verifiable Rewards (RLVR) to mathematical and coding domains has demonstrated significant improvements in the reasoning and problem-solving abilities of ... 4.00 0% See Reviews View AI Dashboard
Null-Space Filtering for Data-free Continual Model Merging: Preserving Transparency, Promoting Fidelity Data-free continual model merging (DFCMM) aims to fuse independently fine-tuned models into a single backbone that evolves with incoming tasks without accessing task data. This paper formulate two fun... 5.50 32% See Reviews View AI Dashboard
The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective In federated learning (FL), model aggregation plays a central role in enabling decentralized knowledge sharing. However, it is often observed that the aggregated model underperforms on local data unti... 4.50 7% See Reviews View AI Dashboard
On Uniformly Scaling Flows: A Density-Aligned Approach to Deep One-Class Classification Unsupervised anomaly detection is often framed around two widely studied paradigms. Deep one-class classification, exemplified by Deep SVDD, learns compact latent representations of normality, while d... 4.00 7% See Reviews View AI Dashboard
OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes There are two prevalent ways to constructing 3D scenes: procedural generation and 2D lifting. Among them, panorama-based 2D lifting has emerged as a promising technique, leveraging powerful 2D generat... 4.50 4% See Reviews View AI Dashboard
PairUni: Pairwise Training for Unified Multimodal Language Models Unified Vision-Language Models (UVLMs) must perform both understanding and generation within a single architecture, but these tasks rely on heterogeneous data and supervision, making it difficult to b... 4.50 17% See Reviews View AI Dashboard
GTA1: GUI Test-time Scaling Agent Graphical user interface (GUI) agents autonomously complete tasks across platforms (\eg, Linux) by sequentially decomposing user instructions into action proposals that iteratively interact with visua... 5.50 5% See Reviews View AI Dashboard
Reasoning at the Right Length: Adaptive Budget Forcing for Efficient and Accurate LLM Inference Large Language Models (LLMs) face persistent challenges in domain-specific reasoning tasks, particularly in fields such as mathematics, telecommunications, and scientific problem-solving, where struct... 3.00 79% See Reviews View AI Dashboard
Entrophy: User Interaction Data from Live Enterprise Workflows for Realistic Model Evaluation AI-driven automation for complex enterprise workflows faces significant hurdles due to the lack of publicly available datasets that realistically capture how business processes unfold - interaction by... 4.00 N/A See Reviews
Reference-based Category Discovery: Unsupervised Object Detection with Category Awareness Traditional one-shot detection methods have addressed the closed-set problem in object detection, but the high cost of data annotation remains a critical challenge. General unsupervised methods genera... 4.00 0% See Reviews View AI Dashboard
Guided Navigation in Knowledge-Dense Environments: Structured Semantic Exploration with Guidance Graphs While Large Language Models (LLMs) exhibit strong linguistic capabilities, their reliance on static knowledge and opaque reasoning processes limits their performance in knowledge-intensive tasks. Alth... 4.00 38% See Reviews View AI Dashboard
SPADE: SEMANTIC-PRESERVING ADAPTIVE DETOXIFICATION OF IMAGES Image generation models often struggle with safety-critical edits, especially detoxifying harmful visual content without losing semantic context. We introduce SPADE, a novel dataset for *controlled, g... 2.50 43% See Reviews View AI Dashboard
VBA: Vector Bundle Attention for Intrinsically Geometry-Aware Learning Learning from geometrically structured data is fundamental in biology, physics, and computer vision. Graph Neural Networks capture local structure but are limited by message passing, while Transformer... 4.67 64% See Reviews View AI Dashboard
Evading Overlapping Community Detection via Proxy Node Injection Protecting privacy in social graphs requires preventing sensitive information, such as community affiliations, from being inferred by graph analysis, without substantially altering the graph topology.... 4.00 26% See Reviews View AI Dashboard
All You Need Are Random Visual Tokens? Demystifying Token Pruning in VLLMs Vision Large Language Models (VLLMs) usually incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising solution for ... 4.00 0% See Reviews View AI Dashboard
COGITAO: A Procedural Object-Centric Framework to Study Compositional Generalization The ability to compose learned concepts and apply them in novel settings is key to human intelligence, but remains a key challenge in state-of-the-art machine learning models. To address this issue, w... 4.00 0% See Reviews View AI Dashboard
How Base Frequency Shapes RoPE: An Analytical Study of Frequency-Band Formation Rotary Position Embeddings (RoPE) are widely adopted in LLMs, and it is commonly believed that larger base frequencies $\theta$ yield better long-context performance. In this paper, we show that a hig... 5.20 0% See Reviews View AI Dashboard
Advanced Image Forensics: Detecting Tampered and AI-Generated Images with Adversarial Learning Detecting image tampering and Artificial Intelligence Generated Images are vital challenges in the fields of computer vision. The primary difficulty in identifying tampered images lies in uncovering m... 2.50 70% See Reviews View AI Dashboard
PLUMAGE: probablistic low-rank unbiased min variance gradient estimation framework for efficient large model training Accelerator memory and network constraints are dominant bottlenecks when training large language models (LLMs) with billions of parameters. Low-rank gradient estimators have been successfully applied ... 4.67 0% See Reviews View AI Dashboard
How is Occam's Razor Realized in Symbolic Regression?: An Adaptive LLM-Enhanced Genetic Programming Approach for Efficient, Versatile, and Interpretable Representation Discovery through Simplification and Evolution Symbolic regression aims to discover mathematical expressions that capture underlying data relationships, but genetic programming (GP) approaches commonly encounter bloat, premature convergence, and i... 3.50 58% See Reviews View AI Dashboard
TokenDrop: Efficient Image Editing by Source Token Drop with Consistency Regularization Text-based image editing has recently been reinterpreted in large multimodal transformers as conditional generation, where source image tokens are concatenated with text and noise tokens as conditioni... 4.50 0% See Reviews View AI Dashboard
HieraQuery: Bridging Multimodal Understanding and High-Quality Generation through Multi-Scale Query Learning Unified multi-modal LLMs enable the integration of visual understanding and generation in a single framework. Recent study shows that a set of learnable queries can serve as an effective interface bet... 4.00 0% See Reviews View AI Dashboard
PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models Large Reasoning Models (LRMs) like Claude 3.7 Sonnet and OpenAI o1 achieve strong performance on mathematical tasks via long Chain-of-Thought (CoT), but often generate unnecessarily verbose reasoning ... 2.67 47% See Reviews View AI Dashboard
Process-Verified Reinforcement Learning for Theorem Proving via Lean While reinforcement learning from verifiable rewards (RLVR) typically has relied on a single binary verification signal, symbolic proof assistants in formal reasoning offer rich, fine-grained structur... 5.00 7% See Reviews View AI Dashboard
Adapting Vision-Language Models for Evaluating World Models World models -- generative models that simulate environment dynamics conditioned on past observations and actions -- are gaining prominence in planning, simulation, and embodied AI. However, evaluatin... 4.67 41% See Reviews View AI Dashboard
Explicit Conditional Consistency Diffusion: Towards Precise Semantic Alignment in Multimodal Face Generation With the collaborative guidance of multimodal conditions (e.g., semantic masks as structural visual guidance and text descriptions as linguistic guidance), diffusion models have significantly improved... 3.50 6% See Reviews View AI Dashboard
LLM-Guided Evolutionary Program Synthesis for Quasi-Monte Carlo Design Low-discrepancy point sets and digital sequences underpin quasi-Monte Carlo (QMC) methods for high-dimensional integration. We cast two long-standing QMC design problems as program synthesis and solve... 4.80 37% See Reviews View AI Dashboard
How Well Can General Vision-Language Models Learn Medicine By Watching Public Educational Videos? Publicly available biomedical videos, such as those on YouTube, serve as valuable educational resources for medical students. Unlike standard machine learning datasets, these videos are designed for h... 4.50 33% See Reviews View AI Dashboard
Structure-Aware Graph Hypernetworks for Neural Program Synthesis We study the neural program synthesis of $\textit{parameterized}$ function families through the lens of meta-learning with hypernetworks. Given a user intent $U$, a meta-learner $M_{\phi}$ produces a ... 4.67 12% See Reviews View AI Dashboard
From Sparse to Dense: Spatio-Temporal Fusion for Multi-View 3D Human Pose Estimation with DenseWarper In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial inf... 4.50 24% See Reviews View AI Dashboard
REVEAL: Advancing Relation-based Video Understanding for Video-Question-Answering Video Question-Answering (Video-QA) comprises the capturing of complex visual relation changes over time, remaining a challenge even for advanced Vision-Language Models (VLM), i.a., because of the nee... 4.50 8% See Reviews View AI Dashboard
The Agent's Marathon: Probing the Limits of Endurance in Long-Horizon Tasks Large Language Model (LLM) agents, augmented with diverse tools, have shown impressive progress in domains such as scientific discovery and enterprise automation. Yet they remain brittle in long-horiz... 3.00 16% See Reviews View AI Dashboard
Blade: A Derivative-free Bayesian Inversion Method using Diffusion Prior Derivative-free Bayesian inversion is an important task in many science and engineering applications, particularly when computing the forward model derivative is computationally and practically challe... 5.00 0% See Reviews View AI Dashboard
Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time We propose a neural physics system for real-time, interactive fluid simulations. Traditional physics-based methods, while accurate, are computationally intensive and suffer from latency issues. Recent... 3.00 4% See Reviews View AI Dashboard
Fine-Grained Iterative Adversarial Attacks with Limited Computation Budget This work tackles a critical challenge in AI safety research under limited compute: given a fixed computation budget, how can one maximize the strength of iterative adversarial attacks? Coarsely reduc... 6.00 9% See Reviews View AI Dashboard
COMPOL: A Unified Neural Operator Framework for Scalable Multi-Physics Simulations Multi-physics simulations play an essential role in accurately modeling complex interactions across diverse scientific and engineering domains. Although neural operators, especially the Fourier Neural... 4.00 47% See Reviews View AI Dashboard
Neurosymbolic Object-Centric Learning with Distant Supervision Relational learning enables models to generalize across structured domains by reasoning over objects and their interactions. While recent advances in neurosymbolic reasoning and object-centric learnin... 5.50 8% See Reviews View AI Dashboard
Assembling the Mind's Mosaic: Towards EEG Semantic Intent Decoding Enabling natural communication through brain–computer interfaces (BCIs) remains one of the most profound challenges in neuroscience and neurotechnology. While existing frameworks offer partial solutio... 6.00 55% See Reviews View AI Dashboard
From Crowds to Codes: Minimizing Review Burden in Conference Review Protocols Conference peer review aims to accurately assess paper quality while minimizing review load. This paper explores optimal conference protocols --- rules for designing review tasks to reviewers and inf... 3.33 0% See Reviews View AI Dashboard
Where Redundancy Lives: Stage-Aware Block Saliency in Skip-Connected Models Residual (skip-connected) architectures such as ResNets are widely used, yet the extent and structure of their inference-time redundancy remain unclear. We repurpose post-training block ablation as a ... 2.50 25% See Reviews View AI Dashboard
Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies Masked diffusion models (MDMs) have recently emerged as a novel framework for language modeling. MDMs generate sentences by iteratively denoising masked sequences, filling in [MASK] tokens step by ste... 5.00 0% See Reviews View AI Dashboard
Counterfactual Digital Twin: Generating What-If Trajectories with Uncertainty Answering \textit{what-if} questions is crucial in many decision-making domains, especially in time-sensitive areas such as healthcare, strategy, and policy. Generating counterfactual trajectories req... 3.33 10% See Reviews View AI Dashboard
PreviousPage 19 of 390 (19490 total rows)Next