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
UniVA: Universal Video Agents towards Next-Generation Video Intelligence Recent breakthroughs in visual AI have largely treated video tasks in isolation, with specialized models excelling at generation, editing, segmentation, or understanding individually. We introduce \te... 4.50 59% See Reviews View AI Dashboard
Fun2spec: Code Contract Synthesis At Scale Specification synthesis -- the problem of inferring program specification from program implementation -- is an undecidable problem. Therefore, machine learning and more specifically, autoregressive la... 4.00 10% See Reviews View AI Dashboard
What Is Missing: Interpretable Ratings for Large Language Model Outputs Current Large Language Model (LLM) preference learning methods such as Proximal Policy Optimization and Direct Preference Optimization rely on direct rankings or numerical ratings of model outputs as ... 1.50 0% See Reviews View AI Dashboard
Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance We propose a step-by-step video-to-audio (V2A) generation method for finer controllability over the generation process and more realistic audio synthesis. Inspired by traditional Foley workflows, our ... 4.50 0% See Reviews View AI Dashboard
Seeing What’s Not There: Negation Understanding Needs More Than Training Understanding the negation in a sentence is an important part of compositional understanding and logic in natural language. Many practical AI applications, such as autonomous driving, include precise ... 5.60 0% See Reviews View AI Dashboard
Transformers tend to memorize geometrically; it is unclear why. We present a clean and analyzable phenomenon that contrasts the predominant *associative* view of Transformer memory with a nascent *geometric* view. Concretely, we present an *in-weights* path-findin... 3.00 0% See Reviews View AI Dashboard
Enjoy Your Layer Normalization with the Computation Efficiency of RMSNorm Layer normalization (LN) is a milestone technique in deep learning and has been widely adopted across various network architectures. However, LN introduces additional computational costs in the infere... 4.50 0% See Reviews View AI Dashboard
Human-Alignment and Calibration of Inference-Time Uncertainty in Large Language Models There has been much recent interest in evaluating large language models for uncertainty calibration to facilitate model control and modulate user trust. Inference time uncertainty, which may provide a... 3.20 0% See Reviews View AI Dashboard
Modality-Aware Quantization: Balancing Visual and Textual Fidelity in Multimodal Compression Vision-language models (VLMs) have achieved remarkable capabilities across multimodal tasks, yet their deployment remains constrained by substantial computational requirements. While post-training qua... 3.33 35% See Reviews View AI Dashboard
When Agents “Misremember” Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them to address complex challenges. However, within thes... 5.50 4% See Reviews View AI Dashboard
ImmunoTrace: A Meta-Agent for Immune History Tracking The adaptive immune system encodes an individual's exposure history in the T-cell receptor (TCR) repertoire. We present ImmunoTrace, an AI agent for immune history tracking that estimates past pathoge... 3.00 40% See Reviews View AI Dashboard
MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems Scaling up data, parameters, and test-time computation has been the mainstream methods to improve LLM systems (LLMsys), but their upper bounds are almost reached due to the gradual depletion of high-q... 4.50 0% See Reviews View AI Dashboard
Structure Learning from Time-Series Data with Lag-Agnostic Structural Prior Learning instantaneous and time-lagged causal relationships from time-series data is essential for uncovering fine-grained, temporally-aware interactions. Although this problem has been formulated as ... 5.50 8% See Reviews View AI Dashboard
From QKV to K/KV: Investigating Minimalist Attention Mechanisms Transformers have become the standard solution for various AI tasks. The widely adopted query, key, and value (QKV) formulation has played a significant role in this. Although the performance of trans... 2.80 14% See Reviews View AI Dashboard
Discrete Feynman-Kac Correctors Discrete diffusion models have recently appeared as a promising alternative to the autoregressive approach for generating discrete sequences. Sample generation via gradual denoising or demasking proce... 5.50 0% See Reviews View AI Dashboard
Architectural Plasticity for Continual Learning Neural networks for continual reinforcement learning (CRL) often suffer from plasticity loss—a progressive decline in their ability to learn new tasks arising from increased churn and Neural Tangent K... 2.50 18% See Reviews View AI Dashboard
Cer-Eval: Certifiable and Cost-Efficient Evaluation Framework for LLMs As foundation models continue to scale, the size of trained models grows exponentially, presenting significant challenges for their evaluation. Current evaluation practices involve curating increasing... 4.67 0% See Reviews View AI Dashboard
Eliminating Steady-State Oscillations in Distributed Optimization and Learning via Adaptive Stepsize Distributed stochastic optimization and learning is gaining increasing traction due to its ability to enable large-scale data processing and model training across multiple agents without the need for ... 3.00 0% See Reviews View AI Dashboard
SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection We propose Self-Augmented Residual 3D Gaussian Splatting (SA-ResGS), a novel framework for stabilizing uncertainty quantification and enhancing uncertainty-aware supervision in next-best-view selectio... 5.00 28% See Reviews View AI Dashboard
Temporal Difference Learning with Constrained Initial Representations Recently, there have been numerous attempts to enhance the sample efficiency of off-policy reinforcement learning (RL) agents when interacting with the environment, including architecture improvements... 2.50 0% See Reviews View AI Dashboard
Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation Recent 3D molecular generation methods primarily use asynchronous auto-regressive or synchronous diffusion models. While auto-regressive models build molecules sequentially, they're limited by a short... 3.50 3% See Reviews View AI Dashboard
Difference-Aware Retrieval Polices for Imitation Learning Behavior cloning suffers from poor generalization to out-of-distribution states due to compounding errors during deployment. We present Difference-Aware Retrieval Polices for Imitation Learning (DARP)... 5.50 0% See Reviews View AI Dashboard
Optimal Dataset Design for Nurture-then-Nature Teaching Designing an optimal dataset to teach a target concept to a learner has been a well-studied problem in Machine Learning. Prior works have mostly focused on unconstrained single-phase teaching, where t... 3.50 0% See Reviews View AI Dashboard
Are Large Vision-Language Models Good Annotators for Image Tagging? Image tagging, a fundamental vision task, traditionally relies on human-annotated datasets to train multi-label classifiers, which incurs significant labor and costs, especially for large-scale label ... 4.67 0% See Reviews View AI Dashboard
Critical Confabulation: Can LLMs Hallucinate for Social Good? LLMs hallucinate, yet some confabulations can have social affordances if carefully bounded. We propose critical confabulation (inspired by critical fabulation from African American Studies), the use o... 6.00 0% See Reviews View AI Dashboard
Addressing divergent representations from causal interventions on neural networks A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encode. Here we ask wheth... 5.20 0% See Reviews View AI Dashboard
Enhancing Tool Calling in LLMs with the International Tool Calling Dataset Tool calling allows large language models (LLMs) to interact with external systems like APIs, enabling applications in customer support, data analysis, and dynamic content generation. Despite recent a... 2.50 38% See Reviews View AI Dashboard
HoloGarment: 360$\degree$ Novel View Synthesis of In-the-Wild Garments Novel view synthesis (NVS) of in-the-wild garments is a challenging task due significant occlusions, complex human poses, and cloth deformations. Prior methods rely on synthetic 3D training data consi... 3.50 0% See Reviews View AI Dashboard
Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods? Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).Despite recent benchmark gains reported for RL, we find that training on these... 3.33 38% See Reviews View AI Dashboard
SPRIG: Improving Large Language Model Performance by System Prompt Optimization Large Language Models (LLMs) have shown impressive capabilities in many scenarios, but their performance depends, in part, on the choice of prompt. Past research has focused on optimizing prompts spec... 4.00 0% See Reviews View AI Dashboard
GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time Repeated Sampling (RS) is a simple inference-time algorithm that has been shown to improve model performance on complex tasks. Although it is an effective way of scaling inference time, it often strug... 6.00 10% See Reviews View AI Dashboard
SimCity: Multi-Agent Urban Development Simulation with Rich Interactions Large Language Models (LLMs) open new possibilities for constructing realistic and interpretable macroeconomic simulations. We present $\textbf{SimCity}$, a multi-agent framework that leverages LLMs t... 3.00 0% See Reviews View AI Dashboard
Probing Confidence Regions for Early Exits in Chain-of-Thought Chain-of-Thought (CoT) has demonstrated remarkable problem-solving capabilities in many large language models (LLMs), but their reasoning processes often exhibit substantial redundancy. To mitigate th... 3.50 19% See Reviews View AI Dashboard
MTS-UNMixers: Multivariate Time Series Forecasting via Channel-Time Dual Unmixing Multivariate time series data provide a robust framework for future predictions by leveraging information across multiple dimensions, ensuring broad applicability in practical scenarios. However, thei... 4.50 40% See Reviews View AI Dashboard
Augmenting Research Ideation with Data: An Empirical Investigation in Social Science Large Language Models (LLMs) show strong potential for generating novel research ideas, yet such ideas often struggle with feasibility and effectiveness. In this paper, we investigate whether augment... 4.67 0% See Reviews View AI Dashboard
MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrieval Zero-shot anomaly detection (ZSAD) often leverages pretrained vision or vision-language models, but many existing methods use prompt learning or complex modeling to fit the data distribution, resultin... 6.00 3% See Reviews View AI Dashboard
MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents Building general-purpose graphical user interface (GUI) agents has become increasingly promising with the progress in vision language models. However, developing effective mobile GUI agents with reinf... 4.50 14% See Reviews View AI Dashboard
Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation Advances in generative medical models are often constrained by modality-specific scenarios that hinder the integration of complementary evidence, such as imaging, pathology, and clinical notes. This f... 4.50 16% See Reviews View AI Dashboard
MIMIC-VQA: COMPILING AGENTIC REASONERS INTO EFFICIENT DOCUMENT VQA MODELS Document Visual Question Answering systems face a fundamental architectural dichotomy: modular agentic frameworks decompose problems into interpretable sub-tasks but incur prohibitive inference latenc... 3.50 69% See Reviews View AI Dashboard
FingER: Fact-Level Answerability for Explainable Refusals in Multi-Hop RAG Large language models (LLMs) are extensively adopted in retrieval-augmented generation (RAG) systems for solving multi-hop reasoning tasks. While prior works effectively utilize retrieved external kno... 3.00 9% See Reviews View AI Dashboard
TimeFK: Towards Time Series Forecasting via Treating LLMs as Fuzzy Key Time series forecasting (TSF) aims to predict future values based on historical data. Recent advancements in large language models (LLMs), which integrate cross-modal information (time series data and... 3.50 22% See Reviews View AI Dashboard
Efficient Differentiable Contact Model with Long-range Influence With the maturation of differentiable physics, its role in various downstream applications—such as model-predictive control, robotic design optimization, and neural PDE solvers—has become increasingly... 5.50 0% See Reviews View AI Dashboard
Multi-Modal Spiking Neural Network for Efficient and Robust Underwater Object Detection Multi-modal artificial neural networks (ANNs) have demonstrated strong performance gains in object detection by leveraging complementary information from diverse data modalities. However, these gains ... 3.00 46% See Reviews View AI Dashboard
LEVERAGING RECURSION FOR EFFICIENT FEDERATED LEARNING Federated learning algorithms perform multiple local updates on clients before communicating with the parameter server to reduce communication overhead and improve overall training efficiency. However... 3.33 0% See Reviews View AI Dashboard
To the Best of Trust: Full-Stage Trusted Multi-modal Clustering Multi-modal clustering (MMC) aims to integrate complementary information from different modalities to uncover latent consistent structures and improve clustering performance.However, existing methods ... 4.00 4% See Reviews View AI Dashboard
From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control Human motion generative modeling aims to synthesize complex motions from daily activities. However, current research is fragmented, focusing on either low-level, short-horizon motions or high-level, d... 4.00 21% See Reviews View AI Dashboard
Collaborative Dual-Size Large Language Models with Dual-Stage Deferral Risk Control Large Language Models (LLMs) have demonstrated remarkable capabilities, yet ensuring their safe deployment remains challenging. Existing safety mechanisms, while effective against malicious inputs, of... 3.00 66% See Reviews View AI Dashboard
CaRe-BN: Precise Moving Statistics for Stabilizing Spiking Neural Networks in Reinforcement Learning Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision-making on neuromorphic hardware by mimicking the event-driven dynamics of biological neurons. However, due to the discret... 4.50 32% See Reviews View AI Dashboard
VerifyThisBench: Generating Code, Specifications, and Proofs All at Once Large language models (LLMs) have demonstrated remarkable progress in code generation, but many existing benchmarks are approaching saturation and offer little guarantee on the trustworthiness of the ... 4.67 17% See Reviews View AI Dashboard
Bayesian Influence Functions for Hessian-Free Data Attribution Classical influence functions face significant challenges when applied to deep neural networks, primarily due to non-invertible Hessians and high-dimensional parameter spaces. We propose the local Bay... 5.50 4% See Reviews View AI Dashboard
PreviousPage 6 of 390 (19490 total rows)Next