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
CLAMP: A Chebyshev-Weighted Multi-Gradient Approach for Multi-Objective LLM Alignment Alignment in large language models (LLMs) is crucial for enhancing their capabilities to align with human preferences. To date, many existing alignment approaches, such as reinforcement learning from... 3.33 0% See Reviews View AI Dashboard
Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward Enhancing the multimodal reasoning capabilities of Multimodal Large Language Models (MLLMs) is a challenging task that has attracted increasing attention in the community. Recently, several studies ha... 6.00 0% See Reviews View AI Dashboard
CMPS: Constrained Mixed Precision Search The increasing complexity of deep neural networks (DNNs) requires effective model compression to reduce their computational and memory footprints for deployment on resource-constrained hardware. Mixed... 2.67 24% See Reviews View AI Dashboard
Unmasking the Tiny: Foreground Probing for Small Object Detection Detecting small objects in high-resolution images is challenging, as small targets are often overwhelmed by the surrounding background and thus prone to being missed or misclassified. To address this ... 4.00 27% See Reviews View AI Dashboard
SpEmoC: Large-Scale Multimodal Dataset for Speaking Segment Emotion Insights Understanding human emotions in spoken conversations is a key challenge in affective computing, with applications in empathetic AI, human-computer interaction, and mental health monitoring. Existing d... 4.67 68% See Reviews View AI Dashboard
Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models Transformers have achieved great success across a wide range of applications, yet the theoretical foundations underlying their success remain largely unexplored. To demystify the strong capacities of ... 4.50 0% See Reviews View AI Dashboard
Generalizable and Consistent Granular Edge Prediction We introduce a new task in edge detection: Granular Edge Prediction. Unlike traditional binary edge maps, this task aims to predict a categorical edge map, where each edge pixel is assigned a granular... 5.00 5% See Reviews View AI Dashboard
None to Optima in Few Shots: Bayesian Optimization with MDP Priors Bayesian Optimization (BO) is an efficient tool for optimizing black-box functions, but its theoretical guarantees typically hold in the asymptotic regime. In many critical real-world applications suc... 4.00 0% See Reviews View AI Dashboard
Constructing coherent spatial memory in LLM agents through graph rectification Given a map description through global traversal navigation instructions (e.g., visiting each room sequentially with action signals such as north, west, etc.), an LLM can often infer the implicit spat... 3.33 66% See Reviews View AI Dashboard
REFLEX-Med: Reinforcement for Label-Free Explainability in Unified Medical Reasoning Clinicians urgently need explanations they can audit, not merely fluent chains. Yet prevailing practices conflate interpretability with subjective human/LLM rationales, with post-hoc visuals loosely a... 3.67 17% See Reviews View AI Dashboard
TimeSqueeze: Dynamic Patching for Efficient Time Series Forecasting Recent progress in time series forecasting has produced large foundation models with strong generalization across domains. However, many of these models rely on transformer backbones, making their eff... 4.29 24% See Reviews View AI Dashboard
GenCompositor: Generative Video Compositing with Diffusion Transformer Video compositing combines live-action footage to create video production, serving as a crucial technique in video creation and film production. Traditional pipelines require intensive labor efforts a... 5.00 0% See Reviews View AI Dashboard
CooperTrim: Adaptive Data Selection for Uncertainty-Aware Cooperative Perception Cooperative perception enables autonomous agents to share encoded representations over wireless communication to enhance each other’s live situational awareness. However, the tension between the limit... 5.33 7% See Reviews View AI Dashboard
Probing to Refine: Reinforcement Distillation of LLM Reasoners via Explanatory Inversion Distilling robust reasoning capabilities from large language models (LLMs) into smaller, computationally efficient student models remains an unresolved challenge. Despite recent advances, distilled mo... 5.67 22% See Reviews View AI Dashboard
BridgeRAG: A Framework for Reasoning over Partitioned Knowledge Graphs Existing Knowledge Graph-based RAG (Retrieval-Augmented Generation) systems face a fundamental dilemma in multi-document scenarios. They either treat each document as an isolated knowledge graph, whic... 2.67 46% See Reviews View AI Dashboard
Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological Imaging Deep learning is now central to radiology, helping detect changes on X-rays, CTs, and MRIs. However, these systems are highly vulnerable to adversarial attacks - small, crafted perturbations that misl... 2.50 1% See Reviews View AI Dashboard
Towards Generalizable Implicit In-Context Learning with Attention Routing Implicit in-context learning (ICL) has newly emerged as a promising paradigm that simulates ICL behaviors in the representation space of Large Language Models (LLMs), aiming to attain few-shot perform... 5.00 0% See Reviews View AI Dashboard
Bridging ML and algorithms: comparison of hyperbolic embeddings Hyperbolic embeddings are well-studied both in the machine learning and algorithm community. However, as the research proceeds independently in those two communities, comparisons and even awareness se... 4.00 0% See Reviews View AI Dashboard
Large Language Model Guided Dynamic Branching Rule Scheduling in Branch-and-Bound Branch-and-bound (B\&B) is a core technique in state-of-the-art mixed integer linear program (MILP) solvers. It reformulates an MILP into a systematic tree search and recursively partitions it into su... 4.00 20% See Reviews View AI Dashboard
Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time We study in-context learning (ICL) of linear regression in a deep linear self-attention model, characterizing how performance depends on various computational and statistical resources (width, depth, ... 5.50 0% See Reviews View AI Dashboard
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models Vision-Language-Action (VLA) models have emerged as a powerful paradigm for robot control through natural language instructions. However, their high inference cost—stemming from large-scale token comp... 4.00 0% See Reviews View AI Dashboard
Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perception Multimodal Large Language Models (MLLMs) require high-resolution visual information to perform fine-grained perception, yet processing entire high-resolution images is computationally prohibitive. Wh... 5.50 7% See Reviews View AI Dashboard
From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization While foundation models (FMs), such as diffusion models and large vision-language models (LVLMs), have been widely applied in educational contexts, their ability to generate pedagogically effective vi... 4.40 41% See Reviews View AI Dashboard
Align Human Camouflaged Perception: Visual Refocus Reinforcement Fine-Tuning Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background. Our observations reveal that these mu... 4.50 28% See Reviews View AI Dashboard
Multimodal Policy Internalization for Conversational Agents Modern conversational agents such as ChatGPT and Alexa+ have become indispensable in everyday life. To handle diverse business requirements and enable agentic capabilities, these LLM-based systems oft... 7.33 0% See Reviews View AI Dashboard
FATE: Focal-modulated Attention Encoder for Multivariate Time-series Forecasting Accurate multivariate time-series forecasting is crucial for understanding and mitigating the effects of climate change, as reliable long-horizon predictions support effective monitoring and informed ... 4.00 N/A See Reviews
Robustify Spiking Neural Networks via Dominant Singular Deflation under Heterogeneous Training Vulnerability Spiking Neural Networks (SNNs) process information via discrete spikes, enabling them to operate at remarkably low energy levels. However, our experimental observations reveal a striking vulnerability... 5.50 4% See Reviews View AI Dashboard
An Optimal Algorithm for Marginalization in Bayesian Networks We study the problem of marginalization in Bayesian networks: given a Bayesian network $G=(V, E)$ and nodes $S$ we wish to marginalize, what is the most compact Bayesian network $G'$ over nodes $V \se... 3.50 0% See Reviews View AI Dashboard
Background Matters: Robust 3D Human Pose Estimation via Controllable Video Generation Deep learning models for 3D human pose estimation (HPE) often fail to generalize across domains with varying environments, camera setups, or data distributions. We address this challenge with a contro... 3.33 21% See Reviews View AI Dashboard
STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models Spoken Language Models (SLMs) are designed to take speech inputs and produce spoken responses. However, current SLMs lack the ability to perform an internal, unspoken thinking process before respondin... 5.00 0% See Reviews View AI Dashboard
Beyond Accuracy: Measuring Reward Variance as a Predictive Benchmark for RLHF Reward models (RMs) provide the core signal in reinforcement learning from human feedback (RLHF). However, most evaluations focus on pairwise accuracy and overlook how the separability and concentrati... 4.00 21% See Reviews View AI Dashboard
Monitoring Decomposition Attacks with Lightweight Sequential Monitors As LLMs become more agentic, a critical risk emerges: attackers can decompose harmful goals into stateful, benign subtasks that trick LLM agents into executing them without realizing the harmful inten... 4.50 0% See Reviews View AI Dashboard
Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities Reasoning on Temporal Knowledge Graphs (TKGs) is essential for predicting future events and time-aware facts. While existing methods are effective at capturing relational dynamics, their performance i... 6.00 69% See Reviews View AI Dashboard
EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences As large language models (LLMs) are deployed globally, creating pluralistic systems that can accommodate the diverse preferences and values of users worldwide becomes essential. We introduce EVALUESTE... 2.67 6% See Reviews View AI Dashboard
G-Verifier: Geometric Verifier for Robust 3D Point Cloud Semantic Search with Spatial Relation Reasoning Semantic search in 3D point clouds is a fundamental task for Spatial Intelligence and embodied AI, yet it becomes particularly challenging when queries involve precise spatial relationships and curren... 2.67 13% See Reviews View AI Dashboard
IDSPACE: A Model-Guided Synthetic Identity Document Generation Framework and Dataset To address the challenges in the lack of data for evaluating identity document fraud detection models provided by vendors or merchants, we propose IDSPACE, a cost-effective framework for generating hi... 4.00 0% See Reviews View AI Dashboard
IBiT: Utilizing Inductive Biases to Create a More Data Efficient Attention Mechanism In recent years, Transformer-based architectures have become the dominant method for Computer Vision applications. While Transformers are explainable and scale well with dataset size, they lack the in... 0.50 0% See Reviews View AI Dashboard
AALawyer: A Generative Retrieval-Augmented Large Language Model System for Legal Reasoning With the growing potential of large language models (LLMs) in the legal domain, an increasing number of specialized legal models are being developed and introduced. Among them, domain-specific finetun... 3.50 0% See Reviews View AI Dashboard
Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks? AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause unintended or harmful behavior. Inspired by the well-esta... 3.50 0% See Reviews View AI Dashboard
Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Thoughts for reasoning tasks. KD methods typically ask... 5.00 0% See Reviews View AI Dashboard
Revisiting the Role of Homophily in Fair Graph Representation Learning Graph Neural Networks (GNNs) can propagate sensitive signals via message passing, especially on homophilous graphs where edges preferentially connect nodes sharing sensitive attributes. We revisit fai... 3.50 28% See Reviews View AI Dashboard
Geometric and Information Compression of Representations in Deep Learning Deep neural networks transform input data into latent representations that support a wide range of downstream tasks. These representations can be characterized along information-theoretic and geometri... 4.00 8% See Reviews View AI Dashboard
STDACN: a Spatiotemporal Prediction Framework based on Dynamic and Adaptive Convolution Networks With the rapid advancement of sensor technologies, analyzing and modeling large spatiotemporal datasets has become crucial, enabling system state predictions for intelligent transportation, urban plan... 3.00 6% See Reviews View AI Dashboard
Simple Stepsizes for Quasi-Newton Methods with Global Convergence Guarantees Quasi-Newton methods are widely used for solving convex optimization problems due to their ease of implementation, practical efficiency, and strong local convergence guarantees. However, their global ... 3.00 0% See Reviews View AI Dashboard
SAS-Bench: A Fine-Grained Benchmark for Evaluating Short Answer Scoring with Large Language Models Short Answer Scoring (SAS) is a critical task in automated subjective answer grading, playing an essential role in education, standardized testing, and large-scale assessment systems. However, existin... 4.50 6% See Reviews View AI Dashboard
PSC: Efficient Grammar-Constrained Decoding via Parser Stack Classification LLMs are widely used to generate structured output like source code or JSON. Grammar-constrained decoding (GCD) can guarantee the syntactic validity of the generated output, by masking out tokens that... 3.50 0% See Reviews View AI Dashboard
APEX: One-Step High-Resolution Image Synthesis The pursuit of efficient text-to-image synthesis has driven the field toward a few-step generation paradigm, yet this endeavor is hampered by a persistent trilemma: achieving high fidelity, inference ... 5.50 22% See Reviews View AI Dashboard
Beyond Pairwise Modeling: Towards Efficient and Robust Trajectory Similarity Computation via Representation Learning Accurate trajectory similarity computation is crucial in ride-sharing applications, where trajectories of varying lengths need to be aligned into a uniform representation. Existing methods suffer from... 4.00 31% See Reviews View AI Dashboard
Shape-Adaptive Guidance Signal for Interactive Cortical Sulcal Labeling Image segmentation is a fundamental task in image data analysis that assigns a semantic label to enhance the understanding of imaging data. In the context of neuroimaging data, the accurate labeling o... 4.00 0% See Reviews View AI Dashboard
Libra-Emo: A Large Dataset for Multimodal Fine-grained Negative Emotion Detection The recognition of negative emotions is pivotal in numerous real-world applications, including public opinion analysis, customer service, emotional attribution, and emotional support systems, where th... 5.00 15% See Reviews View AI Dashboard
PreviousPage 2 of 390 (19490 total rows)Next