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
Batch Speculative Decoding Done Right Speculative decoding speeds up LLM inference by using a small draft model to propose multiple tokens that a target model verifies in parallel. Extending this idea to batches is essential for productio... 4.67 49% See Reviews View AI Dashboard
Disentangling Primitive Representation Structures for Image Generation This paper explains a neural network for image generation from a new perspective, i.e., explaining representation structures for image generation. We propose a set of desirable properties to define th... 4.50 0% See Reviews View AI Dashboard
Pulp Motion: Framing-aware multimodal camera and human motion generation Treating human motion and camera trajectory generation separately overlooks a core principle of cinematography: the tight interplay between actor performance and camera work in the screen space. In t... 4.50 0% See Reviews View AI Dashboard
Adaptive Decoding via Latent Preference Optimization During language model decoding, it is known that using higher temperature sampling gives more creative responses, while lower temperatures are more factually accurate. However, such models are commonl... 4.00 0% See Reviews View AI Dashboard
Openhelix: Empirical Analysis of Dual-System VLA Models for Robotic Manipulation Dual-system vision-language-action (VLA) architectures are emerging as a promising approach in embodied intelligence. However, current works lack consistency in training and evaluation protocols acros... 5.00 0% See Reviews View AI Dashboard
Sparkle: A Robust and Versatile Representation for Point Cloud-based Human Motion Capture Point cloud-based motion capture leverages rich spatial geometry and privacy-preserving sensing, but learning robust representations from noisy, unstructured point clouds remains challenging. Existing... 6.00 27% See Reviews View AI Dashboard
Joint Optimization for 4D Human-Scene Reconstruction in the Wild Reconstructing human motion and its surrounding environment is crucial for understanding human-scene interaction and predicting human movements in the scene. While much progress has been made in captu... 5.50 0% See Reviews View AI Dashboard
Quantum Learning from Label Proportion Learning from Label Proportions (LLP) is a weakly supervised learning method in which training data are provided as bags of instances annotated only with class proportions. We introduce Q-LLP, a quan... 1.67 5% See Reviews View AI Dashboard
Doubly Robust Monte Carlo Tree Search We present Doubly Robust Monte Carlo Tree Search (DR-MCTS), a novel algorithm that integrates doubly robust off-policy estimation into MCTS to improve sample efficiency in computationally expensive en... 3.33 88% See Reviews View AI Dashboard
Unified Single Transformer for Multimodal Video Understanding and Generation With the advancement of language models, unified multimodal understanding and generation have made significant strides, with model architectures evolving from separated components to unified single-mo... 3.50 0% See Reviews View AI Dashboard
Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents The utility of Role-Playing Language Agents in sociological research is growing alongside the adoption of Large Language Models. For realism in social simulation, these agents must adhere to their per... 6.50 12% See Reviews View AI Dashboard
In-Context Reinforcement Learning through Bayesian Fusion of Context and Value Prior In-context reinforcement learning (ICRL) promises fast adaptation to unseen environments without parameter updates, but current methods either cannot improve beyond the training distribution or requir... 4.50 0% See Reviews View AI Dashboard
Evolving Graph Structured Programs for Circuit Generation with Large Language Models Logic synthesis (LS), which aims to generate a *compact* logic circuit graph with minimized size while *accurately* satisfying a given functionality, plays an important role in chip design. However, e... 5.50 2% See Reviews View AI Dashboard
CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs Recently, efficient Multimodal Large Language Models (MLLMs) have gained significant attention as a solution to their high computational complexity, making them more practical for real-world applicati... 6.00 0% See Reviews View AI Dashboard
Pivot-Centric Trajectory Prediction: Bridging Long Horizons via Dynamical Guidance Forecasting precise future motion of surrounding agents is essential for reliable autonomous vehicles. However, as the demand for longer prediction horizons increases, existing endpoint-completion or ... 4.00 0% See Reviews View AI Dashboard
When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity LLM-judged benchmarks are increasingly used to evaluate complex model behaviors, yet their design introduces failure modes absent in conventional, ground-truth–based benchmarks. We argue that, without... N/A 0% See Reviews View AI Dashboard
DiffInk: Glyph- and Style-Aware Latent Diffusion Transformer for Text to Online Handwriting Generation Deep generative models have advanced text-to-online handwriting generation (TOHG), which aims to synthesize realistic pen trajectories conditioned on textual input and style references. However, most ... 5.50 15% See Reviews View AI Dashboard
Decoding Layer by Layer: Uncovering Hierarchical Reasoning in Language Models Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by humans' hierarchical reasoning capability, we propose that a hierarchical decoder architecture cou... 4.50 0% See Reviews View AI Dashboard
WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval Composed Image Retrieval (CIR) task aims to retrieve target images based on reference images and modification texts. Current CIR methods primarily rely on fine-tuning vision-language pre-trained model... 5.00 0% See Reviews View AI Dashboard
From Contextual Distributions to Messages: Entropy-Guided GNNs The Message Passing Neural Networks (MPNNs) have emerged as the dominant framework for learning on graphs. However, their expressive power is fundamentally restricted by the 1-dimensional Weisfeiler-L... 3.00 8% See Reviews View AI Dashboard
PointArena: Probing Multimodal Grounding Through Language-Guided Pointing Pointing serves as a fundamental and intuitive mechanism for grounding language within visual contexts, with applications spanning robotics, assistive technologies, and interactive AI systems. While r... 4.50 44% See Reviews View AI Dashboard
LUCID: Attention with Preconditioned Representations Softmax-based dot-product attention is a cornerstone of Transformer architectures, enabling remarkable capabilities such as in-context learning. However, as context lengths increase, a fundamental lim... 4.00 10% See Reviews View AI Dashboard
Semantic-Aware and Self-Transformative Function Name Recovery for Binaries Reverse engineers aim to analyze stripped binaries in order to identify and mitigate software vulnerabilities. Unlike source code, real-world binaries contain limited semantic information, as companie... 3.00 8% See Reviews View AI Dashboard
Scaling Curriculum Learning for Autonomous Driving Batched simulators for autonomous driving have recently enabled the training of reinforcement learning agents on a massive scale, encompassing thousands of traffic scenarios and billions of interactio... 5.00 0% See Reviews View AI Dashboard
Recursive Autoregressive Depth Estimation with Continuous Token Modeling Monocular depth estimation is a cornerstone of robotic perception and computer vision, yet reconstructing 3-D structure from a single RGB image suffers from severe geometric ambiguity and uncertainty.... 4.00 37% See Reviews View AI Dashboard
Controllable diffusion-based generation for multi-channel biological data Biological profiling technologies, such as imaging mass cytometry (IMC) and spatial transcriptomics (ST), generate multi-channel data with strong spatial alignment and complex inter-channel relationsh... 3.50 11% See Reviews View AI Dashboard
Verl-Tool: Towards Holistic Agentic Reinforcement Learning with Tool Use Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated success in enhancing LLM reasoning capabilities, but remains limited to single-turn interactions without tool integration. While ... 4.50 25% See Reviews View AI Dashboard
Transductive and Learning-Augmented Online Regression Motivated by the predictability of real-life data streams, we study online regression when the online learner has access to predictions about future examples. In the extreme case, called transductive ... 5.00 0% See Reviews View AI Dashboard
Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks Graph Neural Networks (GNNs) are increasingly integrated with federated learning (FL) to protect data locality in domains such as social networks, finance, and biology. While membership inference atta... 4.50 14% See Reviews View AI Dashboard
Sparsity Forcing: Reinforcing Token Sparsity of MLLMs Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods merely exploit a model’s... 5.00 0% See Reviews View AI Dashboard
OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems Large Language Models (LLMs) have demonstrated impressive capabilities in solving a wide range of tasks. However, their ability to iteratively optimize complex solutions by learning from previous feed... 3.00 34% See Reviews View AI Dashboard
Refusal Degrades with Token-Form Drift: Limits of Token-Level Alignment Safety alignment of large language models (LLMs) is typically learned through supervised fine-tuning and preference optimization on a fixed distribution of token sequences. We show that this process c... 5.00 48% See Reviews View AI Dashboard
Factor Graph Optimization for Belief Propagation Decoding Belief Propagation (BP) is a highly efficient message-passing algorithm for inference on graphical models, famously applied to the decoding of sparse codes. The performance of BP, however, is critical... 4.00 0% See Reviews View AI Dashboard
Incremental Learning of Vision-Language Models via Task Subspace Projection and Dynamic LoRA Recent pre-trained vision-language models usually face a Multi-Domain Task-Incremental Learning (MTIL) benchmark in practice, where a set of classes of multi-modal tasks arrive incrementally. Due to p... 3.00 0% See Reviews View AI Dashboard
mR3: Multilingual Rubric-Agnostic Reward Reasoning Models Evaluation using Large Language Model (LLM) judges has been widely adopted in English and shown to be effective for automatic evaluation. However, their performance does not generalize well to non-Eng... 3.50 0% See Reviews View AI Dashboard
Finite‑Time Bounds for Distributionally Robust TD Learning with Linear Function Approximation Distributionally robust reinforcement learning (DRRL) focuses on designing policies that achieve good performance under model uncertainties. In particular, we are interested in maximizing the worst-ca... 4.00 0% See Reviews View AI Dashboard
Steering Language Models with Weight Arithmetic Providing high-quality feedback to Large language models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in un... 5.33 0% See Reviews View AI Dashboard
How Transformers Get Rich: Approximation and Dynamics Analysis Transformers have demonstrated exceptional in-context learning capabilities, yet the theoretical understanding of the underlying mechanisms remains limited. A recent work (Elhage et al., 2021) identif... 4.50 0% See Reviews View AI Dashboard
Policy Optimization Prefers The Path Of Least Resistance Policy optimization (PO) algorithms are used to refine Large Language Models (LLMs) for complex, multi-step reasoning. Current state-of-the-art pipelines enforce a strict think-then-answer format to e... 2.50 66% See Reviews View AI Dashboard
OmniLayout: Enabling Coarse-to-Fine Learning with LLMs for Universal Document Layout Generation Document AI has advanced rapidly and is attracting increasing attention. Yet, while most efforts have focused on document layout analysis (DLA), its generative counterpart, document layout generation,... 3.50 2% See Reviews View AI Dashboard
Identify Critical KV Cache in LLM Inference from an Output Perturbation Perspective Large language models have revolutionized natural language processing but face significant challenges of high storage and runtime costs, due to the transformer architecture's reliance on self-attentio... 5.00 N/A See Reviews
Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement Retrieval-augmented generation (RAG) improves performance on knowledge-intensive tasks but can be derailed by wrong, irrelevant, or conflicting retrieved text, causing models to rely on inaccurate evi... 5.50 18% See Reviews View AI Dashboard
CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models We propose a novel framework designed to improve both the training efficiency and generation quality of multi-view diffusion models. While these models have emerged as a powerful paradigm for novel vi... 3.00 6% See Reviews View AI Dashboard
Agentic reinforcement learning for search is unsafe Agentic reinforcement learning (RL) trains large language models to autonomously call external tools during reasoning, with search as the most common application. These models perform well on multi-st... 5.00 0% See Reviews View AI Dashboard
IPOD:Inverse-Problem-Driven Meta-Learning for Fast Generalizable Neural Representations in MRI Reconstruction Implicit neural representation (INR) demonstrates strong performance in magnetic resonance imaging (MRI) reconstructions by learning continuous mappings from spatial coordinates to signal intensities.... 4.67 8% See Reviews View AI Dashboard
SuperF: Neural Implicit Fields for Multi-Image Super-Resolution High-resolution imagery is often hindered by limitations in sensor technology, atmospheric conditions, and costs. Such challenges occur in satellite remote sensing, but also with handheld cameras, suc... 5.50 0% See Reviews View AI Dashboard
Membership Inference Attacks for Unseen Classes The state-of-the-art for membership inference attacks on machine learning models is a class of attacks based on \emph{shadow models} that mimic the behavior of the target model on subsets of held-out ... 3.50 0% See Reviews View AI Dashboard
BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Behavioural Change This paper introduces the Behavioral Ambivalence/Hesitancy (BAH) dataset collected for the Ambivalence/Hesitancy (A/H) recognition task in videos. In particular, this task involves recognizing conflic... 5.50 4% See Reviews View AI Dashboard
On the Spectral Differences Between NTK and CNTK and Their Implications for Point Cloud Recognition The Convolutional Neural Tangent Kernel (CNTK) offers a principled framework for understanding convolutional architectures in the infinite-width regime. However, a comprehensive spectral comparison be... 6.00 0% See Reviews View AI Dashboard
Dynamic Speculative Agent Planning Despite their remarkable success in complex tasks propelling widespread adoption, large language model based agents still face critical deployment challenges due to prohibitive latency and inference c... 5.50 N/A See Reviews
PreviousPage 7 of 390 (19490 total rows)Next