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
Learning from Few Samples with Language-Model Guidance We consider the problem of learning a classifier from a small set of high-dimensional datapoints, with access to domain knowledge from a language model or human expert. How should such domain knowledg... 4.67 2% See Reviews View AI Dashboard
VUGEN: Visual Understanding priors for GENeration Recent advances in Vision-Language Models (VLMs) have enabled unified understanding across text and images, yet equipping these models with robust image generation capabilities remains challenging. E... 4.00 0% See Reviews View AI Dashboard
PRISON: Unmasking the Criminal Potential of Large Language Models As large language models (LLMs) advance, concerns about their misconduct in complex social contexts intensify. Existing research has overlooked the systematic assessment of LLMs’ criminal potential in... 5.33 34% See Reviews View AI Dashboard
Towards One-step Causal Video Generation via Adversarial Self-Distillation Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long infer... 6.00 5% See Reviews View AI Dashboard
LEMUR: Leveraging Vision-Language Models for Fine-Grained Multimodal Retrieval Fine-grained multimodal retrieval is crucial for many real-world applications. For example, E-commerce product search demands retrieving the product with the most relevant image and description based ... 3.00 0% See Reviews View AI Dashboard
Synthetic History: Evaluating Visual Representations of the Past in Diffusion Models As Text-to-Image (TTI) diffusion models become increasingly influential in content creation, growing attention is being directed toward their societal and cultural implications. While prior research h... 6.00 36% See Reviews View AI Dashboard
SFedPO: Streaming Federated Learning with a Prediction Oracle under Temporal Shifts Federated Learning (FL) enables decentralized clients to collaboratively train a global model without sharing raw data. However, most existing FL frameworks assume that clients train on static local d... 4.50 16% See Reviews View AI Dashboard
Memory Makes The Poison: Over Memorization Drives Visual Poisoning in LVLMs **The poison is not the pixels.** Large Vision–Language Models (LVLMs) excel across tasks, yet their safety and security remain underexplored. Among threats, \textit{visual perturbation–based data poi... 2.00 0% See Reviews View AI Dashboard
LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training Digital agents require diverse, large-scale UI trajectories to generalize across real-world tasks, yet collecting such data is prohibitively expensive in both human annotation, infra and engineering p... 3.00 0% See Reviews View AI Dashboard
Rethinking Transformer Inputs for Time-Series via Neural Temporal Embedding Transformer-based models, originally introduced in the field of natural language processing (NLP), have recently demonstrated strong performance in time-series forecasting. Due to the order-agnostic n... 3.00 5% See Reviews View AI Dashboard
On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference Test-time compute (TTC) has become an increasingly prominent paradigm for enhancing large language models (LLMs). Despite the empirical success of methods such as best-of-$n$ (BoN) sampling and sequen... 4.50 0% See Reviews View AI Dashboard
Automated Architecture Synthesis for Arbitrarily Structured Neural Networks This paper proposes a novel perspective on the architecture of Artificial Neural Networks (ANNs). Conventional ANNs often adopt predefined tree-like or Directed Acyclic Graph (DAG) structures for simp... 3.00 4% See Reviews View AI Dashboard
WaterSearch: A Quality-Aware Search-based Watermarking Framework for Large Language Models In the era of large language models (LLMs), watermarking serves as a crucial safeguard for ensuring accountability, authenticity, and trust in machine-generated text. Text generated by LLMs can be ide... 4.00 5% See Reviews View AI Dashboard
Bridge Policy: Visuomotor Policy Learning via Stochastic Optimal Control Imitation learning has been widely used in robotic learning, where policies are derived from expert demonstrations. Recent advances leverage generative models, such as diffusion and flow-based methods... 3.50 0% See Reviews View AI Dashboard
RegionReasoner: Region-Grounded Multi-Round Visual Reasoning Large vision-language models have achieved remarkable progress in visual reasoning, yet most existing systems rely on single-step or text-only reasoning, limiting their ability to iteratively refine u... 5.00 18% See Reviews View AI Dashboard
Generative Model via Quantile Assignment Deep Generative models (DGMs) play two central roles in modern machine learning: (i) producing new information (e.g., image synthesis, data augmentation, and creative content generation) and (ii) redu... 5.00 8% See Reviews View AI Dashboard
In Agents We Trust, but Who Do Agents Trust? Latent Preferences Steer LLM Generations Large Language Model (LLM) based agents are increasingly being deployed as user-friendly front-ends on online platforms, where they filter, prioritize, and recommend information retrieved from the pla... 4.50 0% See Reviews View AI Dashboard
Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks. However, their vulnerability to adversarial prompts remains a serious concern, as safety mechanisms often f... 4.50 15% See Reviews View AI Dashboard
RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models Real-world databases are predominantly relational, comprising multiple interlinked tables that contain complex structural and statistical dependencies. Learning generative models on relational data h... 4.67 3% See Reviews View AI Dashboard
Improving Medical Visual Reinforcement Fine-Tuning via Perception and Reasoning Augmentation While recent advances in Reinforcement Fine-Tuning (RFT) have shown that rule-based reward schemes can enable effective post-training for large language models, their extension to cross-modal, vision-... 4.00 5% See Reviews View AI Dashboard
Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, t... 5.33 24% See Reviews View AI Dashboard
Optimal Pricing for Bundles: Using Submodularity in Offline and Online Settings We study revenue-maximizing bundle pricing under a cardinality constraint: in each offer the seller chooses a bundle $S\subseteq[n]$ with $|S|\le k$ and posts a single price $p(S)$. Buyers have unknow... 4.00 4% See Reviews View AI Dashboard
ProSAR: Prototype-Guided Semantic Augmentation and Refinement for Time Series Contrastive Learning Contrastive learning has advanced the representation learning of vision, language, and graphs, yet its success hinges greatly on the data augmentation that helps preserve semantic contents while provi... 4.50 22% See Reviews View AI Dashboard
DAG-Math: Graph-Guided Mathematical Reasoning in LLMs Large Language Models (LLMs) demonstrate strong performance on mathematical problems when prompted with Chain-of-Thought (CoT), yet it remains unclear whether this success stems from search, rote proc... 6.00 0% See Reviews View AI Dashboard
Evaluating LLM In-Context Few-Shot Learning on Legal Entity Annotation Task The emergence of Large Language Models (LLMs) has attracted attention due to their powerful in-context few-shot learning capability. Recent studies present significant results regarding its usage in d... 2.50 0% See Reviews View AI Dashboard
UMCI: A Unified Counterfactual Framework for Robust Vision-Language Reasoning Integrating Large Language Models into vision-language frameworks has led to the rise of powerful Large Vision-Language Models (LVLMs). However, this integration introduces two critical robustness cha... 4.50 0% See Reviews View AI Dashboard
RM-R1: Reward Modeling as Reasoning Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thi... 5.00 5% See Reviews View AI Dashboard
Improving and Accelerating Offline RL in Large Discrete Action Spaces with Structured Policy Initialization Reinforcement learning in combinatorial action spaces requires searching over exponentially many joint actions to simultaneously select multiple sub-actions that form coherent combinations. Existing a... 5.00 5% See Reviews View AI Dashboard
Robust Strength Behavior Modeling of Coarse-Grained Soils Using HSIC-Guided Stable Learning Coarse-grained soils are widely employed in infrastructure construction, and capturing their strength behavior is vital for ensuring the structural integrity of engineering systems. In recent years, a... 2.40 27% See Reviews View AI Dashboard
GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-Guided Latent Diffusion Model? Image super‑resolution (SR) is fundamental to many vision systems—from surveillance and autonomy to document analysis and retail analytics—because recovering high‑frequency details, especially scene-t... 5.00 10% See Reviews View AI Dashboard
Value-Anchored Group Policy Optimization for Flow Models Group Relative Policy Optimization (GRPO) has proven highly effective in enhancing the alignment capabilities of Large Language Models (LLMs). However, current adaptations of GRPO for the flow matchin... 3.50 15% See Reviews View AI Dashboard
LLMs Can Generate a Better Answer by Aggregating Their Own Responses Large Language Models (LLMs) have shown remarkable capabilities across tasks, yet they often require additional prompting techniques when facing complex problems. While approaches like self-correction... 2.00 16% See Reviews View AI Dashboard
Self-Guidance: Training VQ-VAE Decoders to be Robust to Quantization Artifacts for High-Fidelity Neural Speech Codec Neural speech codecs, predominantly based on Vector-Quantized Variational Autoencoders (VQ-VAEs), serve as fundamental audio tokenizers for speech large language models (SLLMs). However, their reconst... 5.00 32% See Reviews View AI Dashboard
Efficient Algorithms for Adversarially Robust Approximate Nearest Neighbor Search We study the Approximate Nearest Neighbor (ANN) problem under a powerful adaptive adversary that controls both the dataset and a sequence of $Q$ queries. For the high-dimensional regime $d = \omega(\... 4.80 0% See Reviews View AI Dashboard
$\textbf{SDPose}$: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation Pre-trained diffusion models provide rich multi-scale latent features and are emerging as powerful vision backbones. While recent works such as Marigold and Lotus adapt diffusion priors for dense pred... 4.00 5% See Reviews View AI Dashboard
Unsupervised Behavioral Tokenization and Action Quantization via Maximum Entropy Mixture Policies with Minimum Entropy Components A fundamental problem in reinforcement learning is how to learn a concise discrete set of behaviors that can be easily composed to solve any downstream task. An effective "tokenization" of behavior re... 4.50 0% See Reviews View AI Dashboard
CAREFL: Context-Aware Recognition of Emotions with Federated Learning Emotion recognition from images is a challenging task due to its dependence on subtle visual cues and contextual information. Recent advances in Vision-Language Models (VLMs) have demonstrated strong ... 4.00 66% See Reviews View AI Dashboard
When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training While Large Language Models (LLMs) hold promise to become autonomous agents, they often explore suboptimally in sequential decision-making. Recent work has sought to enhance this capability via superv... 6.00 0% See Reviews View AI Dashboard
Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models Multimodal pre-trained models (e.g., ImageBind), which align distinct data modalities into a shared embedding space, have shown remarkable success across downstream tasks. However, their increasing ad... 4.00 0% See Reviews View AI Dashboard
Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models Multimodal Large Language Models have demonstrated impressive capabilities across tasks, yet they often exhibit difficulty in distinguishing task-relevant from irrelevant signals—particularly in tasks... 5.00 16% See Reviews View AI Dashboard
Optimizing the Ineffable: Generative Policy Learning for Human-Centered Decision-Making Algorithmic decision-making is widely adopted in high-stakes applications affecting our daily lives but often requires human decision-makers to exercise their discretion within the process to ensure a... 4.50 0% See Reviews View AI Dashboard
Certifying Robustness of Agent Tool-Selection Under Adversarial Attacks Large language models (LLMs) are increasingly deployed in agentic systems where they map user intents to relevant external tools to fulfill a task. A critical step in this process is tool selection, w... 4.50 41% See Reviews View AI Dashboard
Gaussian Belief Propagation Network for Depth Completion Depth completion aims to predict a dense depth map from a color image with sparse depth measurements. Although deep learning methods have achieved state-of-the-art (SOTA), effectively handling the spa... 4.50 10% See Reviews View AI Dashboard
All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning The rapid proliferation of AI-generated images (AIGIs) highlights the pressing demand for generalizable detection methods. In this paper, we establish two key principles for AIGI detection task throug... 5.50 3% See Reviews View AI Dashboard
IQA-Octopus: Unified Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring We present IQA-Octopus, the first image quality assessment (IQA) framework that unifies reasoning, grounding, and referring. Built upon large multi-modality models (LMMs), IQA-Octopus is designed to p... 4.00 0% See Reviews View AI Dashboard
Hallucination Mitigation in Large Vision-Language Models via Adaptive Multi-Subspace Projection Recent advances in large vision-language models (LVLMs) have enabled powerful multimodal reasoning by integrating visual encoders with large language models (LLMs). However, their reliability is frequ... 4.00 53% See Reviews View AI Dashboard
Deformable Contact-Aware 3D Object Placement We study language-guided object placement in real 3D scenes when contact is \emph{deformable and frictional}. Rather than guessing a rigid pose that “looks right,” we cast placement as a \emph{drop-to... 3.00 25% See Reviews View AI Dashboard
Reframing Dense Action Detection (RefDense): A New Perspective on Problem Solving and a Novel Optimization Strategy In dense action detection, we aim to detect multiple co-occurring actions. However, action classes are often ambiguous, as they share overlapping sub-components. We argue that the dual challenges of t... 3.50 0% See Reviews View AI Dashboard
Grid-Based Evolutionary Algorithm for Multi-Objective Molecule Generation Enhanced by Reinforcement Learning Fragment-based drug discovery (FBDD) is limited by the need to construct and maintain static fragment libraries. To overcome these challenges, we propose a novel evolutionary framework. Our method sta... 4.00 25% See Reviews View AI Dashboard
ChartAlignBench: A Benchmark for Chart Grounding & Dense Alignment Charts play important roles in visualization, reasoning, and communication in data analysis and idea exchange between humans. However, vision-language models (VLMs) still lack accurate understanding o... 2.00 0% See Reviews View AI Dashboard
PreviousPage 6 of 390 (19490 total rows)Next