Can a 8B-parameter language model produce provably valid multi-step plans instead of plausible guesses? MIT CSAIL researchers introduce PDDL-INSTRUCT, an instruction-tuning framework that couples logical chain-of-thought with external plan validation (VAL) to lift symbolic planning performance of LLMs. On PlanBench,…
Even suffused in otherworldly fog, Silent Hill F’s picturesque period setting gleams with authenticity. Traditional hardwood buildings line narrow alleyways, while babbling brooks and small footpaths crisscross soaking paddy fields. The ephemera of 1960s everyday life is everywhere: glossy magazines,…
The UK-based automaker has been forced to stop vehicle production as a result of the attack—costing JLR tens of millions of dollars and forcing its parts suppliers to lay off workers.
arXiv:2408.12199v2 Announce Type: replace-cross Abstract: The vast and complicated large-qubit state space forbids us to comprehensively capture the dynamics of modern quantum computers via classical simulations or quantum tomography. Recent progress in quantum learning theory prompts a crucial question: can…
arXiv:2502.19668v4 Announce Type: replace-cross Abstract: Cardiovascular diseases are a leading cause of death and disability worldwide. Electrocardiogram (ECG) is critical for diagnosing and monitoring cardiac health, but obtaining large-scale annotated ECG datasets is labor-intensive and time-consuming. Recent ECG Self-Supervised Learning…
arXiv:2505.18475v2 Announce Type: replace Abstract: Graphs are a widely used paradigm for representing non-Euclidean data, with applications ranging from social network analysis to biomolecular prediction. While graph learning has achieved remarkable progress, real-world graph data presents a number of challenges…
arXiv:2509.05165v2 Announce Type: replace Abstract: Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache compression…
arXiv:2404.19501v2 Announce Type: replace Abstract: Bayes’ rule describes how to infer posterior beliefs about latent variables given observations, and inference is a critical step in learning algorithms for latent variable models (LVMs). Although there are exact algorithms for inference and…
arXiv:2502.09969v3 Announce Type: replace Abstract: Influence functions provide crucial insights into model training, but existing methods suffer from large computational costs and limited generalization. Particularly, recent works have proposed various metrics and algorithms to calculate the influence of data using…
arXiv:2509.15279v1 Announce Type: new Abstract: While large language models show promise in medical applications, achieving expert-level clinical reasoning remains challenging due to the need for both accurate answers and transparent reasoning processes. To address this challenge, we introduce Fleming-R1, a…
