arXiv:2509.11629v2 Announce Type: replace Abstract: As large language models (LLMs) continue to advance in capabilities, ensuring their safety against jailbreak attacks remains a critical challenge. In this paper, we introduce a novel safety alignment approach called Answer-Then-Check, which enhances LLM…
arXiv:2603.05739v1 Announce Type: new Abstract: Best-of-N (BoN) sampling is a widely used inference-time alignment method for language models, whereby N candidate responses are sampled from a reference model and the one with the highest predicted reward according to a learned…
arXiv:2511.05664v2 Announce Type: replace Abstract: Masked diffusion models have demonstrated competitive results on various tasks including language generation. However, due to its iterative refinement process, the inference is often bottlenecked by slow and static sampling speed. To overcome this problem,…
arXiv:2603.05760v1 Announce Type: new Abstract: Multi-objective reinforcement learning (MORL) is effective for multi-echelon combinatorial supply chain optimisation, where tasks involve high dimensionality, uncertainty, and competing objectives. However, its deployment in dynamic environments is hindered by the need for task-specific retraining…
arXiv:2512.19554v3 Announce Type: replace Abstract: Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stall; when one happens to be correct, the update usually ignores…
arXiv:2603.05761v1 Announce Type: new Abstract: Rectified Flow (RF) models achieve state-of-the-art generation quality, yet controlling them for precise tasks — such as semantic editing or blind image recovery — remains a challenge. Current approaches bifurcate into inversion-based guidance, which suffers…
arXiv:2602.10956v3 Announce Type: replace Abstract: Spatio-temporal models analyze spatial structures and temporal dynamics, which makes them prone to information degeneration among space and time. Prior literature has demonstrated that over-squashing in causal attention or temporal convolutions creates a bias on…
arXiv:2603.05764v1 Announce Type: new Abstract: Autonomous coding agents can produce strong tabular baselines quickly on Kaggle-style tasks. Practical value depends on end-to-end correctness and reliability under time limits. This paper introduces TML-Bench, a tabular benchmark for data science agents on…
arXiv:2603.02002v3 Announce Type: replace Abstract: Foundation MLIPs demonstrate broad applicability across diverse material systems and have emerged as a powerful and transformative paradigm in chemical and computational materials science. Equivariant MLIPs achieve state-of-the-art accuracy in a wide range of benchmarks…
arXiv:2603.05768v1 Announce Type: new Abstract: Model merging integrates multiple task-specific models into a single consolidated one. Recent research has made progress in improving merging performance for in-distribution or multi-task scenarios, but domain generalization in model merging remains underexplored. We investigate…
