This work introduces a conservative, fully auditable spell-correction reliability layer conceived as a safety-oriented preprocessing module rather than a maximal-accuracy corrector: under conditions of uncertainty, the system abstains from editing, in accordance with a medical do-no-harm philosophy.
Moustafa Mohamed Hassan, Sharon Wong, Woh Kai Xuan· International Conference on...· 0 citations
Results provide initial evidence that KV states can serve as transferable computational representations rather than strictly model-local caches, and motivate context mobility as a systems abstraction for reducing redundant prefill across heterogeneous LLM and multi-agent inference workflows.
Yi Li, Dongming Jiang, Yi Zhao et al.· 0 citations
This work calls on the stream-learning community to make bounded resource usage a first-class design objective alongside drift adaptation, and proposes concrete steps toward this goal, including an API through which stream learners can explicitly expose and respect resource budgets.
Sebastian Buschjäger, N. Gunasekara, H. Gomes· 0 citations
This work releases BAITBENCH, a suite of three synthetic tabular ML tasks that each contain a shortcut that allows agents to inflate the public test score but fail on a hidden test set, and releases an annotated dataset of transcripts containing reward hacks as a testbed for evaluating reward-hacking mitigations head-to-head.
Pradyumna Shyama Prasad, M. Anto, Leon Eshuijs et al.· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
DyTrim is proposed, a principle-based dynamic pruning framework that reallocates gradient budget through class-aware pruning on labeled data and confidence-based soft pruning on unlabeled data and provides theoretical guarantees that DyTrim reduces class bias and improves generalization.
Yue Cheng, Jia-Jun Zhang, Xiao-Hui Gao et al.· 1 citation
Learning materials properties from scarce labels and unlabeled crystals is a central challenge for data-driven materials discovery. We present SemiMat, a controlled benchmark for semi-supervised materials property regression, and MatRank, a reliability-weighted objective for continuous pseudo-label uncertainty. SemiMat fixes labeled and unlabeled crystal inputs, graph-backbone interfaces, validation-only checkpoint selection, held-out test reporting, normalized MAE (NMAE), and method-rank summaries across six scarce-label tasks, four graph backbones, and five predefined split runs. MatRank builds pseudo-targets from labeled anchors, weights them by local reliability and weak-prediction agreement, trains weak and strong graph views consistently, and adds ranking signals so that unlabeled crystals shape both values and candidate order. Across the retained 24 backbone-task blocks, one fixed MatRank objective gives the lowest aggregate held-out test NMAE (0.896) and best average method rank (2.208). The component, OOD, and generated-pool diagnostics identify where the gain is reliable and where further screening evaluation remains necessary. Code is available at https://github.com/littlepeachs/SemiMat.
Wen-Tao Li, Yi-Zhe Chen, Jiang-Jie Qiu et al.· 0 citations
CoMPASS is presented, a retrieval-calibrated framework for small-large model collaboration that retains a graph attention network as the predictive anchor, retrieves locally relevant training molecules, provides attention-grounded evidence to an LLM, and converts its proposal into a bounded correction through an agreement-aware gate.
Wen-Tao Li, Jiang-Jie Qiu, Yi-Jun Li et al.· 0 citations
The AUC is shown to be non-collapsible because it decomposes into within- and cross-group AUC terms when subpopulations coexist, such that its overall value may fall outside the range of subgroup specific AUCs.
João Matos, B. van Calster, Richard D. Riley et al.· 0 citations
Q-Strata is proposed, a bi-level allocator that ranks within-block assignments with a cheap proxy and allocates across blocks with a model-level objective evaluated on the assembled quantized model, achieving lower WikiText2 perplexity than uniform-bitwidth GPTQ and the state-of-the-art MoE MPQ methods MxMoE and GEMQ in the low-bit regime.
This work proposes Neural Double Q-routing, which replaces destination-indexed tables with a shared state--action value network, and achieves the lowest mean completion time among all compared methods in the six 150- and 200-OHT settings, whereas Dijkstra remains best in the three 100-OHT settings.
Chen-Feng Gu, Qiu-Sheng Zhao, An-Bang Liu et al.· 0 citations
This survey provides a structured entry point to tensorized language models and clarifies when parameter savings can plausibly translate into memory efficiency, computational efficiency, or interpretability, and introduces a metric for the compression-realization gap between theoretical memory reduction and measured system-level speedup.
M. Tarasov, Salman Ahmadi-Asl, A. D. de Almeida et al.· 0 citations
Topo^2, a measurement framework that makes deep networks causally separable, measurable, and law-governed, and turns"memorization" from an ill-defined capacity into a measurable, separable, invertible topological layer.
