Calibration Data Trade
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Calibration Data Trade-offs Across Capability Dimensions: Why Multi-Source Mixing Matters for High-Sparsity LLM Pruning
arXiv:2606.03328v2 Announce Type: replace Abstract: Post-training pruning compresses large language models to high sparsity using a small unlabelled calibration set, and recent work has concluded that the choice of calibration source has only modest impact on averaged post-pruning accuracy. We ask whether this conclusion survives once calibration impact is evaluated separately across distinct capability dimensions rather than aggregated. Decomposing post-pruning capability into General,...
Calibration Data Trade-offs Across Capability Dimensions: Why Multi-Source Mixing Matters for High-Sparsity LLM Pruning
arXiv:2606.03328v1 Announce Type: new Abstract: Post-training pruning compresses large language models to high sparsity using a small unlabelled calibration set, and recent work has concluded that the choice of calibration source has only modest impact on averaged post-pruning accuracy. We ask whether this conclusion survives once calibration impact is evaluated separately across distinct capability dimensions rather than aggregated. Decomposing post-pruning capability into General,...
Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning
Announce Type: replace Abstract: We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capacity to imagine and choose -- to simulate future scenarios, weigh trade-offs, and act with calibrated uncertainty. We reframe open radio access network (O-RAN) near-real-time (Near-RT) control via counterfactual dynamics and a world modeling (WM) paradigm that learns an action-conditioned generative state space. This enables quantitative "what-if" forecasting beyond...
ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess
arXiv:2606.04473v1 Announce Type: new Abstract: We present ChessMimic, a system of three small encoder-only transformers - for move, thinking-time, and outcome prediction - conditioned on the position, recent move history, player rating, and clock state. We fit a separate instance of each model per 100-Elo rating band, trading parameter efficiency for sharper per-skill calibration. On a held-out month-wide slice of Lichess Rated Blitz games ChessMimic's human move prediction accuracy...
Deep learning four decades of human migration
Abstract Human migration is a fundamental driver of global demographic change, shaping population structure, labour markets and social policy across countries1,2,3. Although long-term migration patterns are often linked to economic development4, they can shift rapidly in response to shocks such as conflict, environmental crises and political change5. Despite its importance, migration remains difficult to measure consistently: existing data are sparse, concentrated in high-income settings and...
Uncertainty-Aware Graph Neural Reconstruction of Urban Temperature Fields from Sparse Sensors under Deployment Constraints
arXiv:2606.02038v1 Announce Type: cross Abstract: Reconstructing spatially continuous daily temperature fields from sparse observations is important for urban climate monitoring and heat-risk analysis, but practical deployments are limited by sensor budgets and spacing constraints. This study proposes an uncertainty-aware graph neural network (GNN) framework for reconstructing daily maximum temperature fields from sparse sensors while supporting distance-constrained sensor placement and...
Uncertainty-Aware Graph Neural Reconstruction of Urban Temperature Fields from Sparse Sensors under Deployment Constraints
arXiv:2606.02038v1 Announce Type: new Abstract: Reconstructing spatially continuous daily temperature fields from sparse observations is important for urban climate monitoring and heat-risk analysis, but practical deployments are limited by sensor budgets and spacing constraints. This study proposes an uncertainty-aware graph neural network (GNN) framework for reconstructing daily maximum temperature fields from sparse sensors while supporting distance-constrained sensor placement and...
From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression
arXiv:2606.02559v1 Announce Type: new Abstract: Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted modules. Existing replacement-based methods share two design constraints: full-layer granularity and contiguous selection. We argue that this is overly restrictive: in fact, redundancy in pretrained transformers is not confined to contiguous regions, nor does it evenly distribute between Attention...
Great mysteries of archaeology: An ancient Amazonian world revealed from the sky
Great mysteries of archaeology: An ancient Amazonian world revealed from the sky Gaby Clark Scientific Editor Andrew Zinin Lead Editor From the air, you see it only through the constant jolt, tilt, and shudder of the low-flying Cessna aircraft. The landscape of the Llanos de Moxos, northern Bolivia, appears as a disconnected patchwork of open grassland savannahs, forest islands, and lakes. It feels random, almost unreadable.
XSSR: Cross-Domain Self-Supervised Representative Selection for Efficient Annotation in Medical Image Segmentation
arXiv:2606.04301v1 Announce Type: new Abstract: Acquiring labeled medical image data is resource-intensive and a challenge further exacerbated in cross-domain scenarios where source and target datasets differ in imaging equipment, population, or clinical site. This study introduces XSSR (Cross-Domain Self-Supervised Representative Selection), a framework designed to minimize annotation effort in the target domain while maintaining robust segmentation performance. XSSR comprises three stages:...