ICLR 2026 Conference Submissions

ComMat: Datasets and Benchmarks from complex materials for graph machine learning
ICLR 2026 Conference Submission21554 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Causal Judge Evaluation (CJE): Auditable, Unbiased Off-Policy Metrics for LLM Systems via Design-by-Projection
Eddie Landesberg
- 19 Sept 2025 (modified: 22 Oct 2025)
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Distribution-Calibrated Inference Time Compute for Thinking LLM-as-a-Judge
ICLR 2026 Conference Submission21552 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Test-Time Scaling for Multistep Reasoning in Small Language Models via A* Search
ICLR 2026 Conference Submission21551 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Projected Neural Additive Models as Universal Approximators
ICLR 2026 Conference Submission21550 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
From Invariant Representations to Invariant Data: Provable Robustness to Spurious Correlations via Noisy Counterfactual Matching
ICLR 2026 Conference Submission21549 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Estimating Semantic Alphabet Size for LLM Uncertainty Quantification
ICLR 2026 Conference Submission21548 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Symbolic Planning Using LLM Agents: A Cut-Based Reprompting Approach
ICLR 2026 Conference Submission21547 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Constrained Preference RLHF
ICLR 2026 Conference Submission21545 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
TANGRAM: A Dataset for FPGA-Based Heterogeneous Systems-on-Chip Optimization
ICLR 2026 Conference Submission21543 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Learning with Coupled Uncertainty
ICLR 2026 Conference Submission21541 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Feedback promotes efficient-coding while attenuating bias in recurrent neural networks
ICLR 2026 Conference Submission21540 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
ICLR 2026 Conference Submission21539 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Deep Learning with Learnable Product-Structured Activations
ICLR 2026 Conference Submission21538 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts
ICLR 2026 Conference Submission21537 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Learning is Forgetting; LLM Training As Lossy Compression
ICLR 2026 Conference Submission21536 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Select the Right Agent: Data-Driven Online Model Selection in Reinforcement Learning
ICLR 2026 Conference Submission21535 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
A Reality Check on Robust Bandit Algorithms for Buffer-Aware Early Exits
ICLR 2026 Conference Submission21534 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Open-Set Recognition Interaction Effects: Modular Gains and Where to Find Them
ICLR 2026 Conference Submission21533 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Don't Shift the Trigger: Robust Gradient Ascent for Backdoor Unlearning
ICLR 2026 Conference Submission21532 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
BDN: Blaschke Decomposition Networks
ICLR 2026 Conference Submission21530 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
IndicJR: A Benchmark for Jailbreak Robustness of Multilingual LLMs in South Asia
ICLR 2026 Conference Submission21528 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Consider Size not Language: Effects of External Evidence in Multilingual Medical Question Answering
ICLR 2026 Conference Submission21527 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
On alignment of unified multimodal large language models
ICLR 2026 Conference Submission21526 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone
Learning to Link: Incorporating Multi-hop QA Examples Improves Dispersed Knowledge Injection
ICLR 2026 Conference Submission21525 Authors
- 19 Sept 2025 (modified: 08 Oct 2025)
- ICLR 2026 Conference Submission
- Readers: Everyone