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
A Diffusion-Based Data Augmentation Approach for Synthetic Human Portraits Dataset Deep learning models have achieved remarkable success in computer vision. However, their generalizability remains limited when applied to new tasks. Data augmentation can help mitigate this issue, but... 0.00 23% See Reviews View AI Dashboard
Towards a Collaborative Memory for Agentic Workflow: Breaking the Prefix Barrier with Segment-Level KV Cache Sharing In LLMs-based multi-agent systems, the Key-Value (KV) cache serves as a critical carrier of agents' working memory, and its efficient reuse is paramount for enhancing the service throughput and infere... 4.00 31% See Reviews View AI Dashboard
Flow Matching with Semidiscrete Couplings Flow models parameterized as time-dependent velocity fields can generate data from noise by integrating an ODE. These models are often trained using flow matching, i.e. by sampling random pairs of noi... 5.00 0% See Reviews View AI Dashboard
Towards Omnidirectional Reasoning: A Dataset, Benchmark, and GRPO-based Method Omnidirectional images (ODIs), with their 360° field of view, provide unparalleled spatial awareness for immersive applications like augmented reality and embodied AI. However, the capability of exist... 2.50 25% See Reviews View AI Dashboard
Conformal Non-Coverage Risk Control (CNCRC): Risk-Centric Guarantees for Predictive Safety in High-Stakes Settings Standard Conformal Prediction (CP) guarantees that prediction sets contain the true label with high probability, but it is *cost-blind*, treating all errors as equally important---a critical limitatio... 4.50 31% See Reviews View AI Dashboard
Revisiting Spectral Representations in Generative Diffusion Models Diffusion models have shown remarkable performance on diverse generation tasks. Recent work finds that imposing representation alignment on the hidden states of diffusion networks can both facilitate ... 3.50 4% See Reviews View AI Dashboard
Outrageously Large Context Windows via RACE Attention -- A Family of Non-Linear Attention that can be calculated in Strictly Linear-Time Quadratic attention strains memory and time, and even FlashAttention on a GH200 (96 GB) cannot complete a a single forward–backward step of a multi-head attention layer at sequence lengths over one mi... 4.00 0% See Reviews View AI Dashboard
CamoDocs: Poisoning Attack against Retrieval-Augmented Language Models As retrieval-augmented generation (RAG) grows in popularity for compensating the knowledge cutoff of pretrained language models, its security concerns have also increased: RAG retrieves external docum... 3.00 0% See Reviews View AI Dashboard
The Sword of DamocleSpeech: Demystifying Jailbreaking Attack in Discrete Token-based Speech Large Language Models Speech Large Language Models (SpeechLLMs) and Omni models have recently achieved remarkable progress in human-like dialogue, prosody, and expressive emotion. How- ever, due to fragmented architectures... 2.50 0% See Reviews View AI Dashboard
Co-Evolving Agents: Learning from Failures as Hard Negatives The rapid progress of large foundation models has accelerated the development of task-specialized agents across diverse domains. However, the effectiveness of agents remains tightly coupled with the q... 4.00 24% See Reviews View AI Dashboard
Estimating Markov Chain Transition Probabilities for Steady Aging Models from $n$-step Data Usage-dependent aging processes of products such as batteries have become increasingly important. However, in general, revealing aging dynamics of discrete time Markov Decision Processes (MDP) from sp... 4.00 0% See Reviews View AI Dashboard
Bayesian Combinatorial Lottery Ticket Machine: Bayes Meets Extremal Combinatorics Inspired by the lottery ticket hypothesis (LTH) suggesting that the redundancy of neural networks (NNs) is useful for regression tasks, this paper demonstrates that the redundancy suggested by \emph{e... 5.50 0% See Reviews View AI Dashboard
WeFT: Weighted Entropy-driven Fine-Tuning for dLLMs Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT)... 4.00 6% See Reviews View AI Dashboard
The Spatial Blindspot of Vision-Language Models Vision-language models (VLMs) have advanced rapidly, but their ability to capture spatial relationships remains a critical blindspot. Current VLMs are typically built with contrastive language-image p... 3.20 5% See Reviews View AI Dashboard
LOSI: Improving Multi-agent Reinforcement Learning via Latent Opponent Strategy Identification In collaborative Multi-Agent Reinforcement Learning (MARL), agents must contend with non-stationarity introduced not only by teammates’ concurrent decisions but also by partially observable and divers... 3.00 52% See Reviews View AI Dashboard
Kaleidoscopic Teaming in Multi Agent Simulations Warning: This paper contains content that may be inappropriate or offensive. AI agents have gained significant recent attention due to their autonomous tool usage capabilities and their integration i... 4.00 0% See Reviews View AI Dashboard
PairBench: Are Vision-Language Models Reliable at Comparing What They See? Understanding how effectively large vision language models (VLMs) compare visual inputs is crucial across numerous applications, yet this fundamental capability remains insufficiently assessed. While ... 3.00 8% See Reviews View AI Dashboard
Less Is More: Generating Time Series with LLaMA-Style Autoregression in Simple Factorized Latent Spaces Generative models for multivariate time series are essential for data augmentation, simulation, and privacy preservation, yet current state-of-the-art diffusion-based approaches are slow and limited t... 3.00 34% See Reviews View AI Dashboard
Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass safety mechanisms. Existing jailbreak methods s... 2.67 55% See Reviews View AI Dashboard
GaussianTrim3R: Controllable 3D Gaussians Pruning for Feedforward models Feed-forward methods offer a promising paradigm for novel-view synthesis, eliminating computationally expensive per-scene optimization. However, current feed-forward approaches typically predict a fix... 5.50 10% See Reviews View AI Dashboard
Simplify In-Context Learning Traditional in-context learning (ICL) enhances the performance and capability of large language models (LLMs) primarily by optimizing decomposition strategies, reformatting, and ordering. However, wh... 3.00 6% See Reviews View AI Dashboard
One-Token Verification for Reasoning LLMs, Anytime, Anywhere Reasoning large language models (LLMs) have recently achieved breakthrough performance on complex tasks such as mathematical problem solving. A widely used strategy to further improve their performanc... 3.50 11% See Reviews View AI Dashboard
More Than a Snapshot: Forcing Temporal Reasoning in Video Segmentation Video Reasoning Segmentation (VRS) inherits the settings of reasoning based on world knowledge and spatial contents, lacking queries demanding temporal reasoning according to the unique temporal dynam... 3.50 0% See Reviews View AI Dashboard
DTR: Towards optimal token compression with data-driven token ranking for efficient visual-language model inference Token compression is crucial for vision-language models (VLMs) inference due to its tremendous computational complexity. Although substantial works with various model-driven methods have been done to ... 4.67 0% See Reviews View AI Dashboard
improving time complexity of sparsification algorithms We improve time complexity of spectral sparsification algorithms, such as Batson, Spielman and Srivastava (BSS-2009), used for iteratively computing spectral sparsifiers of n-vertex graphs or, more ge... 3.00 0% See Reviews View AI Dashboard
ConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers Diffusion models have demonstrated strong capabilities in generating high-quality images. However, as model size increases, the growing memory footprint and inference latency pose significant challeng... 3.00 8% See Reviews View AI Dashboard
JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks Fake news undermines societal trust and decision-making across politics, economics, health, and international relations, and in extreme cases threatens human lives and societal safety. Because fake ne... 4.50 4% See Reviews View AI Dashboard
LLMTrace: A Corpus for Classification and Fine-Grained Localization of AI-Written Text The widespread use of human-like text from Large Language Models (LLMs) necessitates the development of robust detection systems. However, progress is limited by a critical lack of suitable training d... 3.00 23% See Reviews View AI Dashboard
Detect, Decide, Unlearn: A Transfer-Aware Framework for Continual Learning Continual learning (CL) aims to continuously learn new tasks from data streams. While most CL research focuses on mitigating catastrophic forgetting, memorizing outdated knowledge can cause negative t... 5.00 12% See Reviews View AI Dashboard
MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning Vision language models (VLMs) are increasingly deployed as controllers with access to external tools for complex reasoning and decision-making, yet their effectiveness remains limited by the scarcity ... N/A 43% See Reviews View AI Dashboard
Universal Model Routing for Efficient LLM Inference Model routing is a simple technique for reducing the inference cost of large language models (LLMs), wherein one maintains a pool of candidate LLMs, and learns to route each prompt to the smallest fea... 6.50 0% See Reviews View AI Dashboard
LLM-HFR-RL: Large Language Model (LLM)-Driven Cross-Modal Fine-Grained Alignment and Reinforcement Learning for the Prediction of Heart Failure Risk Predicting Heart Failure Risk (HFR) using electronic health records (EHR) and generating actionable clinical decisions face significant challenges, including integrating multimodal data, modeling long... 1.50 39% See Reviews View AI Dashboard
Read the Room: Video Social Reasoning with Mental-Physical Causal Chains "Read the room," or the ability to infer others’ mental states from subtle social cues, is a hallmark of human social intelligence but remains a major challenge for current AI systems. Existing social... 5.50 11% See Reviews View AI Dashboard
GeoBench: Rethinking Multimodal Geometric Problem-Solving via Hierarchical Evaluation Geometric problem solving constitutes a critical branch of mathematical reasoning, requiring precise analysis of shapes and spatial relationships. Current evaluations of geometric reasoning in vision-... 5.50 9% See Reviews View AI Dashboard
ECHO: Efficient Coarse-Grained Hybrid Optimization — Clip at Batch, Learn at Token Reinforcement learning (RL) for large language models (LLMs) typically employs token-level clipping of importance sampling ratios to ensure training stability. While effective at preventing catastroph... 3.50 61% See Reviews View AI Dashboard
Randomly Sampled Language Reasoning Problems Elucidate Limitations of In-Context Learning While LLMs have revolutionized the field of machine learning due to their high performance on a strikingly wide range of problems, they are also known to hallucinate false answers and underperform on ... 3.50 0% See Reviews View AI Dashboard
AgentXploit: End-to-End Red-Teaming for AI Agents Powdered by Multi-Agent Systems AI agents, powered by Large Language Model (LLM), are vulnerable to indirect prompt injection attacks, where malicious data from external tools and data sources can manipulate agent behavior. Existing... 3.33 34% See Reviews View AI Dashboard
Through BabyAI Steps: Understanding and Evaluating Grounded Intelligence in LLMs Does spatial prediction translate to spatial planning in LLMs? We investigate this question through a controlled experimental test bed using a textual adaptation of the procedurally generated BabyAI g... 3.50 36% See Reviews View AI Dashboard
ViRL-TSC: Enhancing Reinforcement Learning with Vision-Language Models for Context-Aware Traffic Signal Control In real-world urban environments, traffic signal control (TSC) must maintain stability and efficiency under highly uncertain and dynamically changing traffic conditions. Although reinforcement learnin... 4.00 28% See Reviews View AI Dashboard
IUT-Plug: A Plug-in tool for Interleaved Image-Text Generation Existing vision language models (VLMs), including GPT-4 and DALL·E, often struggle to preserve logic, object identity, and style in multimodal image-text generation. This limitation significantly hind... 4.00 64% See Reviews View AI Dashboard
Latent Feature Alignment: Discovering Biased and Interpretable Subpopulations in Face Recognition Models Modern face recognition models achieve high overall accuracy but continue to exhibit systematic biases that disproportionately affect certain subpopulations. Conventional bias evaluation frameworks re... 4.50 35% See Reviews View AI Dashboard
Allusive Adversarial Examples via Latent Space in Multimodal Large Language Models Multimodal large language models (MLLMs) generate text by conditioning on heterogeneous inputs such as images and text. We present allusive adversarial examples, a new class of attacks that impercepti... 4.50 5% See Reviews View AI Dashboard
Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding Diagrams convey symbolic information in a visual format rather than a linear stream of words, making them especially challenging for AI models to process. While recent evaluations suggest that vision-... 3.00 26% See Reviews View AI Dashboard
InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottl... 7.33 0% See Reviews View AI Dashboard
PDE Solvers Should Be Local: Fast, Stable Rollouts with Learned Local Stencils Neural operator models for solving partial differential equations (PDEs) often rely on global mixing mechanisms—such as spectral convolutions or attention—which tend to oversmooth sharp local dynamics... 2.50 56% See Reviews View AI Dashboard
Collaborative Deterministic–Probabilistic Forecasting for Diverse Spatiotemporal Systems Probabilistic forecasting is crucial for real-world spatiotemporal systems, such as climate, energy, and urban environments, where quantifying uncertainty is essential for informed, risk-aware decisio... 4.00 9% See Reviews View AI Dashboard
Hierarchical Multi-Stage Recovery Framework for Kronecker Compressed Sensing In this paper, we study the Kronecker compressed sensing problem, which focuses on recovering sparse vectors using linear measurements obtained using the Kronecker product of two or more matrices. We ... 6.00 0% See Reviews View AI Dashboard
Efficient and Sharp Off-Policy Learning under Unobserved Confounding We develop a novel method for personalized off-policy learning in scenarios with unobserved confounding. Thereby, we address a key limitation of standard policy learning: standard policy learning assu... 5.33 0% See Reviews View AI Dashboard
HELLoRA: Hot Experts Layer-level Low-Rank Adaptation for MOE Model Low-Rank Adaptation (LoRA) has become the dominant paradigm for Parameter-Efficient Fine-Tuning (PEFT) of large language models. However, most prior work focuses on dense architectures. In contrast, M... 4.00 0% See Reviews View AI Dashboard
Credal Graph Neural Networks for Robust Uncertainty Quantification Uncertainty quantification is essential for deploying reliable Graph Neural Networks (GNNs), where existing approaches primarily rely on Bayesian inference or ensembles. In this paper, we introduce th... 4.50 8% See Reviews View AI Dashboard
PreviousPage 14 of 390 (19490 total rows)Next