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
Enzyme-Unified: Learning Holistic Representations of Enzyme Function with a Hybrid Interaction Model Predicting diverse functional properties of enzymes is a crucial challenge in biotechnology. Current machine learning approaches often fall short due to two key limitations: they predict properties in... 4.00 47% See Reviews View AI Dashboard
VL-JEPA: Joint Embedding Predictive Architecture for Vision-language We introduce VL-JEPA, a vision-language model built on a Joint Embedding Predictive Architecture (JEPA). Instead of autoregressively generating tokens as in classical VLMs, VL-JEPA predicts continuous... 6.00 0% See Reviews View AI Dashboard
Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility Transformers are widely used across data modalities, and yet the principles distilled from text models often transfer imperfectly. In this paper, we analyze Transformers through the lens of rank struc... 6.50 0% See Reviews View AI Dashboard
Reinforced Preference Optimization for Recommendation Recent breakthroughs in large language models (LLMs) have fundamentally shifted recommender systems from discriminative to generative paradigms, where user behavior modeling is achieved by generating ... 6.00 0% See Reviews View AI Dashboard
HSG-12M: A Large-Scale Dataset of Spatial Multigraphs from the Energy Spectra of non-Hermitian Crystals AI is transforming scientific research by revealing new ways to understand complex physical systems, but its impact remains constrained by the lack of large, high-quality domain-specific datasets. A r... 4.50 5% See Reviews View AI Dashboard
SPATIAL CONFORMAL INFERENCE THROUGH LOCALIZED QUANTILE REGRESSION Reliable uncertainty quantification at unobserved spatial locations, particularly for complex and heterogeneous datasets, is a key challenge in spatial statistics. Traditional methods like Kriging rel... 4.67 22% See Reviews View AI Dashboard
KVCompose: Efficient Structured KV Cache Compression with Composite Tokens Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in... 3.50 53% See Reviews View AI Dashboard
Fair Bayesian Model-Based Clustering Fair clustering has become a socially significant task with the advancement of machine learning and the growing demand for trustworthy AI. Group fairness ensures that the proportions of each sensitive... 5.20 0% See Reviews View AI Dashboard
Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences Conversion of spoken mathematical expressions is a challenging task that involves transcribing speech into a strictly structured symbolic representation while addressing the ambiguity inherent in the ... 5.00 4% See Reviews View AI Dashboard
What We Don't C: Manifold Disentanglement for Structured Discovery Accessing information in learned representations is critical for annotation, discovery, and data filtering in disciplines where high-dimensional datasets are common. We introduce What We Don't C, a no... 4.00 0% See Reviews View AI Dashboard
VC-Bench: Pioneering the Video Connecting Benchmark with a Dataset and Evaluation Metrics Current video generation techniques mainly focus on creating under text or image conditioning. However, real-world applications often require seamlessly connecting two independent video clips. To addr... 4.00 8% See Reviews View AI Dashboard
KPF: DOMINATING MULTI-AGENT ADVERSARIAL COMPETITION VIA KALMAN-INSPIRED POLICY FU- SION MECHANISM Despite rapid advancements in Multi-Agent Reinforcement Learning (MARL), its application to complex, highly stochastic, and dynamic environments has been hindered by limitations in generalization capa... 3.50 20% See Reviews View AI Dashboard
Rethinking the Definition of Unlearning: Suppressive Machine Unlearning Machine unlearning, an emerging issue of privacy concern in the deep learning era, is practically motivated by the *data removal* from training or *knowledge suppression* of utility on that data. Unfo... 2.50 8% See Reviews View AI Dashboard
Towards Visual Text Grounding of Multimodal Large Language Model Despite the existing evolution of Multimodal Large Language Models (MLLMs), a non-neglectable limitation remains in their struggle with visual text grounding, especially in text-rich images of documen... 4.50 0% See Reviews View AI Dashboard
Proof-Augmented Retrieval and Reasoning: Supervising Language models for Knowledge Graph Completion with Link Predictors We propose Proof-Augmented Retrieval and Reasoning (PARR), a Rewrite-Retrieve-Read framework that leverages interpretable link predictors to supervise the retrieval and reasoning of LLMs for Knowledge... 4.00 0% See Reviews View AI Dashboard
WoW!: World Models in a Closed-Loop World Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow embodied agents with predictive perception for decisio... 7.00 4% See Reviews View AI Dashboard
Foundation for Chinese Poetry Research: An Open Large-Scale and Fine-Grained Multimodal Knowledge Graph Classical Chinese poetry is a treasured cultural heritage of humanity, attracting extensive research interest. However, the study of classical Chinese poetry is hindered by the lack of open, large-sca... 3.50 0% See Reviews View AI Dashboard
Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution Large Language Models (LLMs) are widely used as automated judges, where practical value depends on both accuracy and trustworthy, risk-aware judgments. Existing approaches predominantly focus on accur... 2.50 44% See Reviews View AI Dashboard
Understanding the Fine-Grained Knowledge Capabilities of Vision-Language Models New vision-language models (VLMs) have made significant progress across a wide range of visual reasoning benchmarks, spanning academic benchmarks, document understanding, and general visual question a... 4.00 5% See Reviews View AI Dashboard
Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization Low latency speech human-machine communication is becoming increasingly necessary as speech technology advances quickly in the last decade. One of the primary factors behind the advancement of speech... 3.50 0% See Reviews View AI Dashboard
Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worlds Causal world models are systems that can answer counterfactual questions about an environment of interest, i.e., predict how it would have evolved if an arbitrary subset of events had been realized di... 4.50 0% See Reviews View AI Dashboard
JARA: Joint Alignment and Reconstruction Architecture for Region-Aware Vision-Language Pretraining Contrastive Language-Image Pretraining (CLIP) shows strong zero-shot transfer capabilities. However, it fails to capture the intrinsic semantic structure within images and performs weak on fine-graine... 2.00 8% See Reviews View AI Dashboard
Generative Universal Verifier as Multimodal Meta-Reasoner We introduce *Generative Universal Verifier*, a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models, providing the fundam... 8.00 0% See Reviews View AI Dashboard
Federated ADMM from Bayesian Duality We propose a new Bayesian approach to derive and extend the federated Alternating Direction Method of Multipliers (ADMM). We show that the solutions of variational-Bayesian objectives are associated w... 4.50 0% See Reviews View AI Dashboard
Implicit Bias and Loss of Plasticity in Matrix Completion: Depth Promotes Low-Rankness We study matrix completion via deep matrix factorization (a.k.a. deep linear neural networks) as a simplified testbed to examine how network depth influences training dynamics. Despite the simplicity ... 5.00 0% See Reviews View AI Dashboard
Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning Inspired by the human learning and memory system, particularly the interplay between the hippocampus and cerebral cortex, this study proposes a dual-learner framework comprising a fast learner and a m... 6.50 0% See Reviews View AI Dashboard
LACONIC: Length-Aware Constrained Reinforcement Learning for LLM Reinforcement learning (RL) has enhanced the capabilities of large language models (LLMs) by enabling self-evolution through reward-driven training. Nevertheless, this process can introduce excessivel... 4.00 12% See Reviews View AI Dashboard
Advancing End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-Training Pixel-space generative models are often more difficult to train and generally underperform compared to their latent-space counterparts, leaving a persistent performance and efficiency gap. In this pap... 5.00 0% See Reviews View AI Dashboard
IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation As the mathematical capabilities of large language models (LLMs) improve, it becomes increasingly important to evaluate their performance on research-level tasks at the frontier of mathematical knowle... 4.00 0% See Reviews View AI Dashboard
ManipEvalAgent: Promptable and Efficient Evaluation Framework for Robotic Manipulation Policies In recent years, robotic manipulation policies have made substantial progress. However, evaluating these policies typically requires large-scale sampling in simulation benchmarks, leading to high time... 4.67 8% See Reviews View AI Dashboard
Risk-Optimal Prediction under Unseen Causal Perturbations Predicting intervention effects is important in various scientific fields, including biomedicine. Classical methods depend on fully specified causal graphs and extensive observational data, while rece... 5.50 0% See Reviews View AI Dashboard
PIPA: An Agent for Protein Interaction Identification and Perturbation Analysis Protein–protein interactions (PPIs) play a fundamental role in the functioning of proteins and the formation of cellular pathways. Given their implication in numerous disease processes, PPIs represent... 2.00 92% See Reviews View AI Dashboard
Slicing Wasserstein over Wasserstein via Functional Optimal Transport Wasserstein distances define a metric between probability measures on arbitrary metric spaces, including *meta-measures* (measures over measures). The resulting *Wasserstein over Wasserstein* (WoW) d... 7.00 0% See Reviews View AI Dashboard
RestoRect: Degraded Image Restoration via Latent Rectified Flow & Feature Distillation Current approaches for restoration of degraded images face a critical trade-off: high-performance models are too slow for practical use, while fast models produce poor results. Knowledge distillation ... 3.50 54% See Reviews View AI Dashboard
On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis Recently, Visual Autoregressive ($\mathsf{VAR}$) Models introduced a groundbreaking advancement in the field of image generation, offering a scalable approach through a coarse-to-fine ``next-scale pre... 2.50 9% See Reviews View AI Dashboard
AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations High-quality scientific illustrations are crucial for effectively communicating complex scientific and technical concepts, yet their manual creation remains a well-recognized bottleneck in both academ... 3.60 8% See Reviews View AI Dashboard
ParetoRouter: VLSI Global Routing with Multi-Objective Optimization Global routing (GR) has been a central task in modern chip design. Many efforts, either ML-based or heuristic, have been proposed, which seek to optimize certain business goals e.g. overflow (OF) and ... 3.50 4% See Reviews View AI Dashboard
ECO grad: Error Correcting Optimization for Quasi-Gradients, a Variable Metric DFO Strategy We introduce a \textit{Quasi-Gradient} method using 0th order directional derivatives and quasi-Newton like updates. Empirically, our method reduces $d$-dependence of zeroth-order problems to an effec... 0.00 0% See Reviews View AI Dashboard
Attention Clusters: Revealing the Inductive Bias of Attention Mechanisms We introduce a parameter-free framework to isolate the self-attention mechanism, stripping away all learned parameters. Through iterative application, we demonstrate that self-attention alone intrinsi... 3.00 7% See Reviews View AI Dashboard
ICDiffAD: Implicit Conditioning Diffusion Model for Time Series Anomaly Detection Time series anomaly detection (TSAD) faces critical challenges from intrinsic data noisiness and temporal heterogeneity, which undermine the reconstruction fidelity of prevailing generative approaches... 4.00 17% See Reviews View AI Dashboard
Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) often suffer in early ... 4.50 N/A See Reviews
What Factors Affect LLMs and RLLMs in Financial Question Answering? Recently, the development of large language models (LLMs) and reasoning large language models (RLLMs) have gained considerable attention from many researchers. RLLMs enhance the reasoning capabilities... 3.00 0% See Reviews View AI Dashboard
NGS-Marker: Robust Native Watermarking for 3D Gaussian Splatting With the rapid development and adoption of 3D Gaussian Splatting (3DGS), the need for effective copyright protection has become increasingly critical. Existing watermarking techniques for 3DGS mainly ... 5.00 5% See Reviews View AI Dashboard
Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations When asked to explain their decisions, large language models (LLMs) can often give explanations which sound plausible to humans. But are these explanations faithful, i.e. do they convey the factors ac... 3.33 0% See Reviews View AI Dashboard
Unlocking Full Efficiency of Token Filtering in Large Language Model Training Token filtering has been proposed to enhance the utility of large language models (LLMs) by eliminating inconsequential tokens during training. While using fewer tokens is expected to reduce computati... 6.00 0% See Reviews View AI Dashboard
Learning to Be Fair: Modeling Fairness Dynamics by Simulating Moral-Based Multi-Agent Resource Allocation Fairness is a foundational social construct for stable, resilient societies, yet its meaning is dynamic, context-dependent, and inherently subjective. This multifaceted nature reveals a gap between tr... 3.50 64% See Reviews View AI Dashboard
Generative Photographic Control for Scene-Consistent Video Cinematic Editing Cinematic storytelling is profoundly shaped by the artful manipulation of photographic elements such as depth of field and exposure. These effects are crucial in conveying mood and creating aesthetic ... 3.50 6% See Reviews View AI Dashboard
HAPDA: A Human-Machine Predictive Discrepancy Adapter for AI-Generated Text Detection Recent advances in large language models (LLMs) have enabled them to generate text with increasingly human-like linguistic styles, posing significant challenges for AI-generated text detection (AGTD).... 4.00 9% See Reviews View AI Dashboard
Draining Your Account: A Stealthy Attack on API Billing in Multi-Agent Systems Multi-Agent Systems (MAS) excel at complex problem-solving tasks by orchestrating specialized agents through the control flow. Agents are empowered by external APIs, accessed via the Model Context Pro... 3.50 4% See Reviews View AI Dashboard
RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection, where attackers embed malicious content into... 6.00 0% See Reviews View AI Dashboard
PreviousPage 12 of 390 (19490 total rows)Next