ICLR 2026 Conference Submissions

Training-Free Native Sparse Attention for KV Cache Compression
ICLR 2026 Conference Submission16673 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Asymmetric Learning Dynamics For Reaching Stackelberg Equilibrium
ICLR 2026 Conference Submission16672 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Graph Transformer Neural Processes
ICLR 2026 Conference Submission16671 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
LoRAMax: Adaptive Low-Rank Gated Module for Extreme-Scale language Style Modeling
ICLR 2026 Conference Submission16669 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions
ICLR 2026 Conference Submission16665 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
ICLR 2026 Conference Submission16664 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability
ICLR 2026 Conference Submission16663 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models
ICLR 2026 Conference Submission16662 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
TRACE: Adaptive Curtailment of Reasoning in Retrieval-Augmented Generation via Trajectory Reflection
ICLR 2026 Conference Submission16661 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Protap: A Benchmark for Protein Modeling on Realistic Downstream Applications
ICLR 2026 Conference Submission16660 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
LayerDecompose: Exploring weight sharing for Large Language Model Compression
ICLR 2026 Conference Submission16659 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Algorithm Generation via Creative Ideation
ICLR 2026 Conference Submission16657 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
F2: Let Large Language Models Think like Aristotle
ICLR 2026 Conference Submission16656 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Dolph2Vec: Self-Supervised Representations of Dolphin Vocalizations
ICLR 2026 Conference Submission16655 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
TTS-Hub: Leveraging Modular LoRAs and Arithmetic Composition for Controllable Text-to-Speech
ICLR 2026 Conference Submission16654 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
How Much Can a Query Reveal? Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction
ICLR 2026 Conference Submission16653 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models
ICLR 2026 Conference Submission16652 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Eliciting Human-like Social Reasoning in Large Language Models
ICLR 2026 Conference Submission16651 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
ALIGNING LLMS WITH GRAPH NEURAL SOLVERS FOR COMBINATORIAL OPTIMIZATION
ICLR 2026 Conference Submission16650 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation
ICLR 2026 Conference Submission16649 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel Optimization
ICLR 2026 Conference Submission16648 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Overshoot and Shrinkage in Classifier-Free Guidance: From Theory to Practice
ICLR 2026 Conference Submission16647 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Learning Compact Regular Decision Processes using Priors and Cascades
ICLR 2026 Conference Submission16646 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Adaptive Masking Enhances Visual Grounding
ICLR 2026 Conference Submission16645 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets
ICLR 2026 Conference Submission16644 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone