ICLR 2026 Conference Submissions

Topology Explains Loss Barriers: Quotient Homology of Neural Loss Landscapes
ICLR 2026 Conference Submission499 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Atomos: Hierarchical Reasoning From Atomic Steps
ICLR 2026 Conference Submission498 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use
ICLR 2026 Conference Submission496 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
ACE-Bench: Benchmarking Agentic Coding in End-to-End Development of Complex Features
ICLR 2026 Conference Submission495 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Efficient Generative Model Training via Embedded Representation Warmup
ICLR 2026 Conference Submission494 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
A Hybrid Paradigm for Vision Autoencoders: Unifying CNNs and Transformers for Learning Efficiency and Scalability
ICLR 2026 Conference Submission493 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities
ICLR 2026 Conference Submission491 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning
ICLR 2026 Conference Submission490 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
How Stable is the Next Token? A Geometric View of LLM Prediction Stability
ICLR 2026 Conference Submission489 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
FG-CLIP 2: A Bilingual Fine-grained Vision-language Alignment Model
ICLR 2026 Conference Submission488 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
FASTer: Toward Powerful and Efficient Autoregressive Vision–Language–Action Models with Learnable Action Tokenizer and Block-wise Decoding
ICLR 2026 Conference Submission487 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Protocode: Prototype-Driven Interpretability for Code Generation in LLMs
ICLR 2026 Conference Submission486 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animation
ICLR 2026 Conference Submission484 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
APEX: One-Step High-Resolution Image Synthesis
ICLR 2026 Conference Submission482 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML
ICLR 2026 Conference Submission480 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
ICLR 2026 Conference Submission477 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
ICLR 2026 Conference Submission475 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
GPS: General Per–Sample Prompter
ICLR 2026 Conference Submission474 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
ICLR 2026 Conference Submission473 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
ICLR 2026 Conference Submission470 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Productive LLM Hallucinations: Conditions, Mechanisms, and Benefits
ICLR 2026 Conference Submission468 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
RegionE: Adaptive Region-Aware Generation for Efficient Image Editing
ICLR 2026 Conference Submission466 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Query Routing over Multimodal Knowledge Bases for Retrieval-Augmented Reasoning
ICLR 2026 Conference Submission465 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering
ICLR 2026 Conference Submission464 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
RESIDUAL-GUIDED MULTI-RESOLUTION REFINEMENT OF FOUNDATION MODELS - A CASE STUDY IN CLIMATE FORECASTING
ICLR 2026 Conference Submission462 Authors
- 01 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone