This work analyzesparse autoencoder features across six models and three SAE families and zero-ablate at full layer depth, finding cross-family claims are sensitive to training methodology, not just activation function or scale.
Seonglae Cho, Zekun Wu, Kleyton Da Costa et al.· arXiv.org· 1 citation
Seq2Synth is introduced, a unified benchmark for assessing temporal and schema properties to determine applicable evaluations, covering timestamp, cross-sectional, longitudinal, and structural fidelity, alongside trajectory-aware utility and privacy.
Kiwan Kwon, Kangmin Kim, Ho-Jin Lee et al.· 0 citations
Tensegrity form-finding and physical property prediction are fundamental problems in structural mechanics, which aim to determine equilibrium configurations and internal force distributions. These problems are challenging due to strong nonlinearity arising from the coupling between geometry and forces, and the need to satisfy equilibrium, stability, and structural constraints. This paper proposes an energy-based learning approach for clustered tensegrity form finding and physical property prediction. The proposed approach incorporates total potential energy minimization and constitutive relations into the training objective, enabling the prediction of equilibrium nodal configurations and the reconstruction of physical quantities such as member forces and force densities. By integrating energy-based physical losses directly into the learning process, the method promotes physical consistency while combining data-driven learning with physics-based constraints. Numerical experiments on tensegrity prism and lander structures demonstrate accurate prediction of equilibrium configurations and internal forces across different training-data ratios, indicating the potential of the proposed approach for nonlinear tensegrity form finding and structural analysis.
Jing Qin, Muhao Chen· National Aerospace and Elect...· 0 citations
The consequence is a measurement instruction rather than a theorem: a transfer conclusion read at one strength does not identify what changed, because a displacement and a gain are not distinguishable from a single operating point.
Lucas Pinto· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A strong, fixed, rule-based expert is built for Gin Rummy and used only as a yardstick, never for training, and the result is a lightweight, game-agnostic recipe that trains competitive agents without training on the expert, for any game a small model can handle, reported with robust statistics and released as a reusable package.
Nima Kelidari, M. Haghi, Mahdi Salmani· arXiv.org· 0 citations
Bounded unfiltered teacher continuations at learner-induced contexts improve over pure behavioral cloning at matched budgets and suggest that a few teacher steps, placed at learner-induced contexts, can be a more cost-efficient supervision allocation than longer or more heavily curated teacher completions.
Junze Ye, Jiayi Cheng, Miao Lu et al.· arXiv.org· 2 citations
Data-Adaptive Lower-Rank Adaptation (DALorRA), a simple and effective variational Bayesian sparse framework that shifts the paradigm of uncertainty quantification from the dense parameter space to the lightweight rank level of low-rank adaptation (LoRA).
Ji-Jie Zhang, Zhenjiang Ren, Quan Zhang et al.· arXiv.org· 0 citations
Through NeuReasoner as a modular, interpretable, theory-grounded elicitation instrument, this work empirically map where reasoning elicitation succeeds and fails, beyond the mathematical and coding benchmarks where prior claims have rested.
MV-WSA (Marginal-Value Working-Set Allocation), which splits memory by marginal latency benefit per byte while enforcing a KV-admission floor, is implemented in WiSP (Working-Set Paging), a routing-aware expert pager that plugs into an unmodified serving engine and preserves byte-identical outputs.
The resulting lesson is task-specific: a first stage for generated controls should be judged by control fidelity, downstream relevance, and graph compatibility together.
Rui Wu, Zongyuan Chen, Hong Xie et al.· 0 citations
CARE is introduced, a reference-conditioned controller that separates program synthesis from experiment selection and attains the lowest normalized regret, the highest normalized best-so-far AUC, and the highest Top-1% Success@15 among the evaluated methods.
Guanyu Liu, Weiyi Kong, Chao Tang et al.· 1 citation
AlignGAD is proposed, a zero-shot generalized graph anomaly detection framework that aligns heterogeneous node features and normalizes graph signals in the spectral domain and demonstrates the effectiveness of AlignGAD under the zero-shot GAD setting.
Phan Nguyen, Dat Cao, Hien Chu et al.· arXiv.org· 0 citations
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
MIT News · Artificial Intelligence· news.mit.eduAug 24, 2026
