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
Geometry-Aware Metric for Dataset Diversity via Persistence Landscapes Diversity can be broadly defined as the presence of meaningful variation across elements, which may be viewed from multiple perspectives, including statistical variation and geometric structural richn... 4.00 30% See Reviews View AI Dashboard
Inducing Dyslexia in Vision Language Models Dyslexia, a neurodevelopmental disorder characterized by persistent reading difficulties, is often linked to reduced activity of the visual word form area in the ventral occipito-temporal cortex. Trad... 4.00 11% See Reviews View AI Dashboard
AToken: A Unified Tokenizer for Vision We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that s... 6.50 35% See Reviews View AI Dashboard
VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision–language alignment, yet they remain limited in visual–spatial reasoning. We first identify that this limitation ari... 5.00 24% See Reviews View AI Dashboard
Worse Together: Understanding the Brittleness of Multimodal Models on Rare Concept Pairs Multimodal models are being deployed in real-world settings where rare or unseen combinations of objects during pretraining are bound to appear at test time. Understanding how these models generalize ... 5.00 0% See Reviews View AI Dashboard
ProxyThinker: Test-Time Guidance through Small Visual Reasoners Recent advancements in reinforcement learning with verifiable rewards have pushed the boundaries of the visual reasoning capabilities in large vision-language models (LVLMs). However, training LVLMs w... 6.00 0% See Reviews View AI Dashboard
Forging Better Rewards: A Multi-Agent LLM Framework for Automated Reward Evolution Large Language Models (LLMs) have shown increased autonomy in performing complex tasks, but the inference latency and fine-tuning cost impose significant limitations for their application in dynamic, ... 4.00 36% See Reviews View AI Dashboard
GREAT: GROUP-ACQUIRED BIPARTITE ALIGNMENT FOR GRAPH FAIRNESS ADAPTATION Graph neural networks (GNNs) have shown strong performance in graph fairness learning, which aims to ensure that predictions are unbiased with respect to sensitive attributes. However, existing approa... 2.67 2% See Reviews View AI Dashboard
Modular Fine-Tuning of Clustering:Directional Updating of Weight Parameters for PLMs With the widespread adoption of pre-trained language models (PLMs) and the pre-training-fine-tuning paradigm, studies have shown that increasing model scale often leads to performance improvements, ye... 3.00 53% See Reviews View AI Dashboard
ZTRS: Zero-Imitation End-to-end Autonomous Driving with Trajectory Scoring End-to-end autonomous driving maps raw sensor inputs directly into ego-vehicle trajectories to avoid cascading errors from perception modules and to leverage rich semantic cues. Existing frameworks la... 3.33 0% See Reviews View AI Dashboard
Bayesian Symbolic Regression with Entropic Reinforcement Learning Symbolic regression is the problem of finding an algebraic expression describing a stochastic dependence of a target variable on a set of inputs. Unlike forms of regression that fit parameters assumin... 3.33 0% See Reviews View AI Dashboard
Adaptive Conformal Prediction via Mixture-of-Experts Gating Similarity Prediction intervals are essential for applying machine learning models in real applications, yet most conformal prediction (CP) methods provide coverage guarantees that overlook the heterogeneity and... 5.00 19% See Reviews View AI Dashboard
S2J: Bridging the Gap Between Solving and Judging Ability in Generative Reward Models With the rapid development of large language models (LLMs), generative reward models (GRMs) have been widely adopted for reward modeling and evaluation. Previous studies have primarily focused on trai... 4.00 3% See Reviews View AI Dashboard
A quantitative analysis of semantic information in deep representations of text and images Deep neural networks are known to develop similar representations for semantically related data, even when they belong to different domains, such as an image and its description, or the same text in d... 3.50 0% See Reviews View AI Dashboard
Improving Diffusion Models for Class-imbalanced Training Data via Capacity Manipulation While diffusion models have achieved remarkable performance in image generation, they often struggle with the imbalanced datasets frequently encountered in real-world applications, resulting in signif... 6.00 0% See Reviews View AI Dashboard
MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks While large audio-language models have advanced open-ended audio understanding, they still fall short of nuanced human-level comprehension. This gap persists largely because current benchmarks, limite... 3.60 0% See Reviews View AI Dashboard
Safe Exploration via Policy Priors Safe exploration is a key requirement for reinforcement learning agents to learn and adapt online, beyond controlled (e.g. simulated) environments. In this work, we tackle this challenge by utilizing ... 7.33 0% See Reviews View AI Dashboard
Learning Compact Vision Tokens for Large Multimodal Models Large multimodal models (LMMs) suffer significant computational challenges due to the high cost of Large Language Models (LLMs) and the quadratic complexity of processing long vision token sequences. ... 4.50 0% See Reviews View AI Dashboard
Fourier Features Let Agents Learn High Precision Policies with Imitation Learning Various 3D modalities have been proposed for high-precision imitation learning tasks to compensate for the short-comings of RGB-only policies. Modalities that explicitly represent positions in Cartesi... 4.00 0% See Reviews View AI Dashboard
What is Missing? Explaining Neurons Activated by Absent Concepts Explainable artificial intelligence (XAI) aims to provide human-interpretable insights into the behavior of deep neural networks (DNNs), typically by estimating a simplified causal structure of the mo... 5.00 0% See Reviews View AI Dashboard
Generative Prompting with Diffusion for Lifelong Continual Adaptation Machine learning models deployed in dynamic environments often face distribution shifts that are not entirely novel but instead recurring and long-term. To capture this practical scenario, we introduc... 3.00 0% See Reviews View AI Dashboard
Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance As machine learning models are increasingly deployed in high-stakes settings, e.g. as decision support systems in various societal sectors or in critical infrastructure, designers and auditors are fa... 5.00 0% See Reviews View AI Dashboard
SubDyve: Subgraph-Driven Dynamic Propagation for Virtual Screening Enhancement Controlling False Positive Virtual screening (VS) aims to identify bioactive compounds from vast chemical libraries, but remains difficult in low-label regimes where only a few actives are known. Existing methods largely rely o... 5.50 N/A See Reviews
POME: Post Optimization Model Edit via Matrix Orthogonalization We revisit a basic question: whether a fine-tuned large language model can be improved after training using only its pretrained and fine-tuned checkpoints, without extra data or further optimization. ... 4.00 33% See Reviews View AI Dashboard
WAPITI: A Watermark for Finetuned Open-Source LLMs Watermarking of large language model (LLM) generations embeds imperceptible statistical patterns within text, enabling algorithmic detection. It provides a promising defense for ensuring traceability,... 3.00 5% See Reviews View AI Dashboard
Training LLMs with LogicReward for Faithful and Rigorous Reasoning Although LLMs exhibit strong reasoning capabilities, existing training methods largely depend on outcome-based feedback, which can produce correct answers with flawed reasoning. Prior work introduces ... 6.50 0% See Reviews View AI Dashboard
SimFLi: Simple Few-Shot Linear Modeling for On-Device LLM Latency Profiling On-device inference of large language models (LLMs) is increasingly central to mobile and edge AI, yet profiling their latency remains challenging: existing methods are often server-centric, rely on o... 3.50 23% See Reviews View AI Dashboard
FiGuRO - Intrinsic Dimension Estimation for Multi-Modal Data A fundamental challenge in representation learning is determining the complexity, or the Intrinsic Dimension (ID), of the data. This becomes especially difficult in the multi-modal setting when trying... 4.50 0% See Reviews View AI Dashboard
Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting We introduce a framework for robust uncertainty quantification in situations where labeled training data are corrupted, through noisy or missing labels. We build on conformal prediction, a statistical... 6.00 0% See Reviews View AI Dashboard
ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Lear... 3.33 5% See Reviews View AI Dashboard
How can we assess human-agent interactions? Case studies in software agent design LLM-powered agents are both a promising new technology and a source of complexity, where choices about models, tools, and prompting can affect their usefulness. While numerous benchmarks measure agent... 5.00 0% See Reviews View AI Dashboard
Search Inspired Exploration for Reinforcement Learning Exploration in environments with sparse rewards remains a fundamental challenge for reinforcement learning (RL). Existing approaches such as curriculum learning and Go-Explore often rely on hand-craft... 3.50 43% See Reviews View AI Dashboard
Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of large pre-trained models. Yet LoRA can face generalization challenges. One promising way to improve the generalization is Sharpnes... 6.00 0% See Reviews View AI Dashboard
Open-Vocabulary Object Detection for Low-Altitude Scenarios Using RGB-Infrared Data: A Benchmark and A New Method Traditional object detection methods are limited by closed datasets, while open-vocabulary object detection (OVOD) overcomes this limitation. However, most existing OVOD approaches are trained on nat... 3.00 9% See Reviews View AI Dashboard
MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports Doctors and patients alike increasingly use Large Language Models (LLMs) to diagnose clinical cases. However, unlike domains such as math or coding, where correctness can be objectively defined by the... 3.00 0% See Reviews View AI Dashboard
Managing Solution Stability in Decision-Focused Learning with Cost Regularization Decision-focused learning is an emerging paradigm that integrates predictive modeling and combinatorial optimization by training models to directly improve decision quality rather than prediction accu... 3.50 0% See Reviews View AI Dashboard
Unraveling Syntax: How Language Models Learn Context-Free Grammars We introduce a new framework for understanding how language models acquire syntax. While large models achieve impressive results, little is known about their learning dynamics. Our approach starts wit... 3.00 0% See Reviews View AI Dashboard
PRS-MED: POSITION REASONING SEGMENTATION IN MEDICAL IMAGING Recent advances in prompt-based medical image segmentation have enabled clinicians to identify tumors using simple input like bounding boxes or text prompts. However, existing methods face challenges ... 2.80 0% See Reviews View AI Dashboard
Chimera: Compositional Image Generation using Part-based Concepting Personalized image generative models are highly proficient at synthesizing images from text or a single image, yet they lack explicit control for composing objects from specific parts of multiple sour... 3.50 6% See Reviews View AI Dashboard
LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D Reconstructing animatable 3D humans from casually captured images of articulated subjects without camera or pose information is highly practical but remains challenging due to view misalignment, occlu... 5.00 0% See Reviews View AI Dashboard
Instruction-Tuned Video-Audio Models Elucidate Functional Specialization in Brain Recent voxel-wise multimodal brain encoding studies have shown that multimodal Transformer models exhibit a higher degree of brain alignment compared to unimodal models in two distinct settings: when ... 5.33 0% See Reviews View AI Dashboard
Dream2Learn: Structured Generative Dreaming for Continual Learning Continual learning struggles with balancing plasticity and stability while mitigating catastrophic forgetting. Inspired by human sleep and dreaming mechanisms, we propose Dream2Learn (D2L), a generati... 4.00 12% See Reviews View AI Dashboard
LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens Large reasoning models (LRMs) have led to new possibilities in terms of problem-solving, through the devising of a natural language thought process prior to answering a query. While their capabilitie... 5.50 0% See Reviews View AI Dashboard
GaugeKV: Composable Exact KV Cache Compression The key–value (KV) cache is a dominant memory cost in long-context Transformer inference. We introduce GaugeKV, a training-free method that leverages the head-wise gauge symmetry of attention to reduc... 4.00 5% See Reviews View AI Dashboard
Lossless Compression: A New Benchmark for Time Series Model Evaluation The evaluation of time series models has traditionally focused on four canonical tasks: forecasting, imputation, anomaly detection, and classification. Although these tasks have made significant progr... 4.80 63% See Reviews View AI Dashboard
MI-Grad-CAM: Letting Your Model Reveal What’s Most Informative With the growing role of machine vision in critical applications such as healthcare, achieving precise and interpretable decision-making is crucial. Class Activation Mapping (CAM) is widely used for v... 3.00 16% See Reviews View AI Dashboard
Uncertainty-Aware Search and Value Models in LLMs Value model-guided search is effective in steering the generation but suffers from verifier failures: imperfect verifiers may mistakenly prune all the valid paths. This limitation could arise from rel... 2.00 0% See Reviews View AI Dashboard
Contextual Causal Bayesian Optimisation We introduce a unified framework for contextual and causal Bayesian optimisation, which aims to design intervention policies maximising the expectation of a target variable. Our approach leverages... 4.50 0% See Reviews View AI Dashboard
Progressive Residual Tensor Networks for Adversarial Purification Adversarial perturbations remain a critical threat to modern vision systems, and tensor network–based purification is a promising direction thanks to its low-rank priors. Yet these methods face a fund... 4.00 71% See Reviews View AI Dashboard
Value Gradient Flow: Behavior-Regularized RL without Regularization We study behavior-regularized reinforcement learning (RL), which encompasses offline RL and RL from human feedback (RLHF). In both settings, regularization toward a reference distribution (offline dat... 5.50 4% See Reviews View AI Dashboard
PreviousPage 4 of 390 (19490 total rows)Next