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
MVP: Memory-enhanced Vision-Language-Action Policy with Feedback Learning Recent advances in Vision-Language-Action (VLA) models have enabled robots to perform a wide range of manipulation tasks conditioned on language instructions, offering strong generalization across tas... 4.00 0% See Reviews View AI Dashboard
DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration We propose DIVERSE, a framework for systematically exploring the Rashomon set of deep neural networks, the collection of models that match a reference model’s accuracy while differing in their predict... 6.00 44% See Reviews View AI Dashboard
Intra-Trajectory Consistency for Reward Modeling Reward models are critical for improving large language models (LLMs), particularly in reinforcement learning from human feedback (RLHF) and inference-time verification. Due to the prohibitive cost of... 3.50 0% See Reviews View AI Dashboard
Never Saddle: Reparameterized Steepest Descent as Mirror Flow How does the choice of optimization algorithm shape a model’s ability to learn features? To address this question for steepest descent methods—including sign descent, which is closely related to Adam—... 3.50 0% See Reviews View AI Dashboard
Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regression We study instrumental variable regression (IVaR) under differential privacy constraints. Classical IVaR methods (like two-stage least squares regression) rely on solving moment equations that directl... 5.50 27% See Reviews View AI Dashboard
From Compression to Specialization: An Information-Preserving Approach for Dense to Mixture-of-Experts Construction The high cost of training Mixture-of-Experts (MoE) models from scratch has spurred interest in converting pre-trained dense models into sparse MoE models. However, existing dense-to-sparse MoE methods... 2.67 33% See Reviews View AI Dashboard
Real-Aware Residual Model Merging for Deepfake Detection Deepfake generators evolve quickly, making exhaustive data collection and repeated retraining impractical. We argue that model merging is a natural fit for deepfake detection: unlike generic multi-tas... 5.50 0% See Reviews View AI Dashboard
Aligning News and Prices: A Cross-Modal LLM-Enhanced Transformer DRL Framework for Volatility-Adaptive Stock Trading While Deep Reinforcement Learning (DRL) has shown promise for stock trading, its practical application is constrained by critical gaps that undermine performance in real-world volatile markets, most n... 2.00 32% See Reviews View AI Dashboard
The Blind Spot of LLM Security: Time-Sensitive Backdoors Activated by Inherent Features With the widespread adoption of Large Language Models (LLMs), backdoor attacks against pre-trained LLMs have become a notable security issue. Without control over end-user inputs, the trigger conditio... 4.50 4% See Reviews View AI Dashboard
Variational Model Merging for Pareto Front Estimation in Multitask Finetuning We propose a new variational model merging method that can yield arbitrarily accurate Pareto fronts in multitask finetuning. The idea is to first compute posterior-approximations on each task separate... 5.00 0% See Reviews View AI Dashboard
ORCaS: Unsupervised Depth Completion via Occluded Region Completion as Supervision We propose a method for inferring an egocentric dense depth map from an RGB image and a sparse point cloud. The crux of our method lies in modeling the 3D scene implicitly within the latent space and... 6.00 0% See Reviews View AI Dashboard
When Can You Get Away with Low Memory Adam? Adam is the go-to optimizer for training modern machine learning models, but it requires additional memory to maintain the moving averages of the gradients and their squares. While various low-memory ... 3.20 0% See Reviews View AI Dashboard
MFCL: A Multi-modal Function Calling Evaluation for Large Language Models Large language models are evolving into multi-modal agents that call tools directly from raw speech or images. Yet we still lack a principled metric for how well they convert perception into accurate ... 4.50 7% See Reviews View AI Dashboard
CaseGen: A Benchmark for Multi-Stage Legal Case Documents Generation Legal case documents play a critical role in judicial proceedings. As the number of cases continues to rise, the reliance on manual drafting of legal case documents is facing increasing pressure and c... 3.00 0% See Reviews View AI Dashboard
Chain of Time: In-Context Physical Simulation with Image Generation Models We propose a novel method to improve the physical simulation ability of vision-language models. This Chain-of-Time simulation is motivated by in-context reasoning in machine learning, and mental simul... 3.00 0% See Reviews View AI Dashboard
$\mathbf{Li_2}$: A Framework on Dynamics of Feature Emergence and Delayed Generalization While the phenomenon of grokking, i.e., delayed generalization, has been studied extensively, it remains an open question whether there is a mathematical framework to characterize what kind of feature... 5.00 0% See Reviews View AI Dashboard
DualTune: Decoupled Fine-tuning for On-Device Agentic Systems The deployment of Large Language Models (LLMs) as agentic orchestrators has revolutionized task automation, but the need for privacy-preserving, cost-effective solutions demands on-device inference ca... 2.50 0% See Reviews View AI Dashboard
NaviAgent: Bilevel Planning on Tool Navigation Graph for Large-Scale Orchestration Large language models (LLMs) have recently demonstrated the ability to act as function call agents by invoking external tools, enabling them to solve tasks beyond their static knowledge. However, exis... 5.50 44% See Reviews View AI Dashboard
TCMAgent: A Multi-Agent Framework for General Traditional Chinese Medicine A central challenge in artificial intelligence is designing systems that replicate expert cognition in domains where decisions require holistic data synthesis and deliberative reasoning. While large l... 2.50 48% See Reviews View AI Dashboard
DynaIP: Dynamic Image Prompt Adapter for Scalable Zero-shot Personalized Text-to-Image Generation Personalized Text-to-Image (PT2I) generation aims to produce customized images based on reference images. A prominent interest pertains to the integration of an image prompt adapter to facilitate zero... 5.00 0% See Reviews View AI Dashboard
Towards a more Holistic Evaluation of Object-Centric Learning Object-centric learning (OCL) methods were developed by taking inspiration from how humans perceive a scene. It is conjectured that they achieve compositional generalisation by decomposing the scene i... 5.00 0% See Reviews View AI Dashboard
Gen-DFL: Decision-Focused Generative Learning for Robust Decision Making Decision-focused learning (DFL) integrates predictive models with downstream optimization, directly training machine learning models to minimize decision errors. While DFL has been shown to provide su... 3.50 28% See Reviews View AI Dashboard
GAMBIT: A Graph-structured and Decision-Aware Benchmark for MoBile GUI Tasks Mobile GUI agents powered by LMMs can perceive screens and follow instructions, yet existing benchmarks largely target short, linear workflows and step-level accuracy, offering limited insight into lo... 4.00 N/A See Reviews
DatasetResearch: Benchmarking Agent Systems for Demand-Driven Dataset Discovery The rapid advancement of large language models has fundamentally shifted the bottleneck in AI development from computational power to data availability—with countless valuable datasets remaining hidde... 4.00 0% See Reviews View AI Dashboard
SafeCoop: Unravelling Full Stack Safety in Agentic Cooperative Driving Collaborative driving systems leverage vehicle-to-everything (V2X) communication across multiple agents to enhance driving safety and efficiency. Traditional V2X systems take raw sensor data, neural f... 3.50 17% See Reviews View AI Dashboard
Neurosymbolic Language Reasoning as Satisfiability Modulo Theory Natural language (NL) contains extensive logical structure, finely meshed with ''gestalt'' content best interpreted statistically. LLMs are indispensable for interpreting the gestalt content but known... 4.50 14% See Reviews View AI Dashboard
How Confident are Video Models? Empowering Video Models to Express their Uncertainty Generative video models demonstrate impressive text-to-video capabilities, spurring widespread adoption in many real-world applications. However, like large language models (LLMs), video generation mo... 5.50 0% See Reviews View AI Dashboard
AdaSpec: Adaptive Spectrum for Enhanced Node Distinguishability Spectral Graph Neural Networks (GNNs) achieve strong performance in node classification, yet their node distinguishability remains poorly understood. We analyze how graph matrices and node features jo... 5.50 7% See Reviews View AI Dashboard
Self-Knowledge Without a Self? Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns Generating reliable, calibrated confidence estimates is critical for deploying LLMs in high-stakes or user-facing applications, and remains an open challenge. Prior research has often framed confidenc... 4.00 0% See Reviews View AI Dashboard
ReCAP: Recursive Prompting for Self-Supervised Category-Level Articulated Pose Estimation from an Image Estimating category-level articulated object poses is crucial for robotics and virtual reality. Prior works either rely on costly annotations, limiting scalability, or depend on auxiliary signals suc... 4.67 11% See Reviews View AI Dashboard
CausalAffect: Causal Discovery for Facial Affective Understanding Understanding human affect from facial behavior requires not only accurate recognition but also structured reasoning over the latent dependencies that drive muscle activations and their expressive out... 5.00 17% See Reviews View AI Dashboard
Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by integrating external knowledge. However, conflicts between parametric knowledge and retrieved context p... 4.50 0% See Reviews View AI Dashboard
LLM Unlearning with LLM Beliefs Large language models trained on vast corpora inherently risk memorizing sensitive or harmful content, which may later resurface in their outputs. Prevailing unlearning methods generally rely on gradi... 6.00 9% See Reviews View AI Dashboard
Layer-wise Sensitivity-aware Sparsity Allocation for Efficient LLM Inference Large Language Model (LLM) inference presents substantial computational challenges when executed on commodity hardware, thereby necessitating the development of efficient acceleration techniques. Whil... 5.33 59% See Reviews View AI Dashboard
In-Context Clustering with Large Language Models We propose In-Context Clustering (ICC), a flexible LLM-based procedure for clustering data from diverse distributions. Unlike traditional clustering algorithms constrained by predefined similarity mea... 2.50 0% See Reviews View AI Dashboard
A Theoretical Analysis of Discrete Flow Matching Generative Models We provide a theoretical analysis for end-to-end training Discrete Flow Matching (DFM) generative models. DFM is a promising discrete generative modeling framework that learns the underlying generati... 4.50 5% See Reviews View AI Dashboard
Improving End-to-End Training of Retrieval-Augmented Generation Models via Joint Stochastic Approximation Retrieval-augmented generation (RAG) has become a widely recognized paradigm to combine parametric memory with non-parametric memory. An RAG model consists of two serial connecting components (retriev... 3.33 0% See Reviews View AI Dashboard
scCMIA: Self-supervised Dual Model for Mitigating Information Loss in Single-cell Cross-Modal Alignment Recent technological advances in single-cell sequencing have enabled simultaneous profiling of multiple omics modalities within individual cells. Despite these advancements, challenges such as high no... 3.00 0% See Reviews View AI Dashboard
WebRAGent: Retrieval-Augmented Generation for Multimodal Web Agent Planning Trajectory data, capturing multimodal human actions and states, are pivotal for building autonomous GUI agents and transferring skills across tasks, encoding knowledge by compressing past experience i... 4.00 0% See Reviews View AI Dashboard
Contrastive Residual Energy Test-time Adaptation Test-Time Adaptation (TTA) enhances model robustness by enabling adaptation to target distributions that differ from training distributions, improving real-world generalizability. However, most existi... 4.50 9% See Reviews View AI Dashboard
SpintBench: Evaluating LLMs' Complex \\ Reasoning via Spatial Integration Challenges Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains, yet their comprehensive spatial reasoning competencies remain underexplored. This paper propose... 3.50 0% See Reviews View AI Dashboard
Label-Free Attribution for Interpretability The importance of attribution algorithms in the AI field lies in enhancing model transparency, diagnosing and improving models, ensuring fairness, and increasing user understanding. Gradient-based att... 4.80 7% See Reviews View AI Dashboard
Bridging Discrete and Continuous RL: Stable Deterministic Policy Gradient with Martingale Characterization The theory of discrete-time reinforcement learning (RL) has advanced rapidly over the past decades. Although primarily designed for discrete environments, many real-world RL applications are inherentl... 4.50 0% See Reviews View AI Dashboard
HIGH-AVATAR: Hierarchical Representation for One-shot Gaussian Head Avatar We propose HIGH-Avatar, a novel one-shot method that leverages a $\textbf{HI}$erarchical representation for animatable 3D $\textbf{G}$aussian $\textbf{H}$ead reconstruction from a single image. In con... 3.50 26% See Reviews View AI Dashboard
Element2Vec: Build Chemical Element Representation from Text for Property Prediction Accurate property data for chemical elements is crucial for materials design and manufacturing, but many of them are difficult to measure directly due to equip- ment constraint. While traditional meth... 2.50 0% See Reviews View AI Dashboard
Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads Solving complex tasks usually requires LLMs to generate long multi-step reasoning chains. Previous work has shown that verifying the correctness of individual reasoning steps can further improve the p... 3.00 0% See Reviews View AI Dashboard
DeepHA: Scaling Action Chains Elicits Deep Hierarchical Agents Prevailing autonomous agents are often constrained by a single, predefined action space, which limits their generalization capabilities across diverse tasks and can introduce compounding errors throug... 3.50 35% See Reviews View AI Dashboard
DeepOmni: Towards Seamless and Smart Speech Interaction with Adaptive Modality-Specific MoE Native multimodal large language models (MLLMs) restructure a single large language model (LLM) into a spoken language model (SLM) capable of both speech and text generation. Compared to modular and a... 4.50 4% See Reviews View AI Dashboard
Probing Memes in LLMs: A Paradigm for the Entangled Evaluation World Current evaluations of large language models (LLMs) often treat datasets and models in isolation, obscuring phenomena that only emerge from their collective interaction. Items in datasets are reduced ... 4.00 0% See Reviews View AI Dashboard
Exploring weightless neural networks: From logic gates to convolutional lookup tables Increasing the intelligence of everyday objects is facilitated by miniaturized machine learning (ML) models which operate accurately in resource-constrained environments. Applications abound across th... 4.00 0% See Reviews View AI Dashboard
PreviousPage 11 of 390 (19490 total rows)Next