arXiv:2603.22216v1 Announce Type: cross Abstract: The slow, sequential nature of autoregressive (AR) language models has driven the adoption of parallel decoding methods. However, these non-AR models often sacrifice generation quality as they struggle to model the complex joint distribution of…
arXiv:2603.20453v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) replaces hard-to-specify rewards with pairwise trajectory preferences, yet regret-oriented theory often assumes that preference labels are generated consistently from a single ground-truth objective. In practical RLHF systems, however, feedback…
arXiv:2406.03736v4 Announce Type: replace Abstract: Discrete diffusion models with absorbing processes have shown promise in language modeling. The key quantities to be estimated are the ratios between the marginal probabilities of two transitive states at all timesteps, called the concrete…
arXiv:2603.20474v1 Announce Type: new Abstract: Conservation laws are fundamental to understanding dynamical systems, but discovering them from data remains challenging due to parameter variation, non-polynomial invariants, local minima, and false positives on chaotic systems. We introduce NGCG, a neural-symbolic pipeline…
arXiv:2505.10347v3 Announce Type: replace Abstract: Specialized Multi-Task Optimizers (SMTOs) balance task learning in Multi-Task Learning by addressing issues like conflicting gradients and differing gradient norms, which hinder equal-weighted task training. However, recent critiques suggest that equally weighted tasks can achieve…
A new model shows how levels of the “atmosphere’s detergent” may rise and fall in response to climate change.
An MIT-led team is designing artificial intelligence systems for medical diagnosis that are more collaborative and forthcoming about uncertainty.
arXiv:2411.17292v2 Announce Type: replace-cross Abstract: Visual Question Answering (VQA) systems are notoriously brittle under distribution shifts and data scarcity. While previous solutions-such as ensemble methods and data augmentation-can improve performance in isolation, they fail to generalise well across in-distribution (IID),…
arXiv:2510.02249v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable reasoning abilities on complex problems using long Chain-of-Thought (CoT) reasoning. However, they often suffer from overthinking, meaning generating unnecessarily lengthy reasoning steps for simpler problems. This issue may…
arXiv:2511.23455v2 Announce Type: replace Abstract: Language models have seen enormous progress on advanced benchmarks in recent years, but much of this progress has only been possible by using more costly models. Benchmarks may therefore present a warped picture of progress…
