Supervised Learning Has a Geometric Blind Spot
arXiv:2604.21395v3 Announce Type: replace-cross Abstract: Ordinary supervised training minimises the task loss and then stops. It never pays for how far the representation moves when the…
Papers 5179 stories
Safe Evolution with Circuit Anchors
arXiv:2608.05158v1 Announce Type: new Abstract: In biological evolution, unconstrained mutation can lead to catastrophic outcomes: organisms may evolve enhanced capabilities while losing essential functions for survival.…
CPC-CMS: Cognitive Pairwise Comparison Classification Model Selection Framework for Document-level Sentiment Analysis
arXiv:2507.14022v2 Announce Type: replace Abstract: This study proposes the Cognitive Pairwise Comparison Classification Model Selection (CPC-CMS) framework for document-level sentiment analysis. The CPC, based on expert…
Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detection
arXiv:2604.04444v2 Announce Type: replace Abstract: Open-vocabulary object detection (OVOD) enables models to detect any object category, including unseen ones. Benefiting from large-scale pre-training, existing OVOD methods…
Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models
arXiv:2608.05243v1 Announce Type: new Abstract: Factorized generative models commonly regularize a latent style variable z_s by matching its marginal distribution to a fixed Gaussian prior and…
Threshold-Based Early Stopping of Accumulations in Neural Networks with Binary Activation
arXiv:2608.06177v1 Announce Type: cross Abstract: Binary neural networks are very attractive for constrained deployment, enabling small footprint and low-power inference. For binary activations, the dot products…
Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning
arXiv:2608.06276v1 Announce Type: new Abstract: Persistence diagrams (PDs) provide stable and interpretable summaries of multiscale topological structure. While substantial progress has been made in the statistical…
When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents
arXiv:2608.05219v1 Announce Type: new Abstract: Privileged on-policy distillation provides dense supervision for multi-turn agents by allowing a synchronized teacher to re-score the student's response at every…
SemiAdapt-Instruct: Extensible Instruction Tuning via Latent Domain-Specialised Adapters
arXiv:2608.05161v1 Announce Type: new Abstract: Instruction-tuned LLMs are deployed into environments where domains evolve, yet extending a fine-tuned model's capabilities without full retraining remains an unsolved…
LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction
arXiv:2608.05600v1 Announce Type: cross Abstract: Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE), whereas online reinforcement learning requires stochastic rollouts…
Text-Guided Refinement of Multi-sequence Glioma Subregion Segmentation with a Vision-Language Foundation Model
arXiv:2608.05389v1 Announce Type: new Abstract: Background: Accurate glioma subregion delineation is important for radiotherapy planning and longitudinal monitoring, but manual contour correction is time-consuming. Models such…
PRISM: Priority-aware Rubric Internalization via Structured Multimodal Data Synthesis
arXiv:2608.05249v1 Announce Type: new Abstract: Real-world multimodal instructions often bundle multiple requirements with unequal importance, yet most multimodal training data still reduce instruction following to answering…
Ge$^text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer
arXiv:2604.08894v2 Announce Type: replace Abstract: Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs). However, they encounter significant deficiencies in training and…
Beyond Marginal Validity: Finite-Sample Guarantees for Localized Conformal Prediction
arXiv:2608.06206v1 Announce Type: new Abstract: Conformal prediction endows arbitrary black-box predictors with finite-sample, distribution-free marginal coverage, yet marginal validity can hide severe covariate-specific miscalibration, while exact…
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
arXiv:2607.28609v2 Announce Type: replace Abstract: Computer-using agents (CUAs) are advancing rapidly across the digital world. A CUA trajectory records the agent's actions, states, and reasoning. Verifying…
InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval
arXiv:2608.04761v2 Announce Type: replace-cross Abstract: Self-improving agents accumulate reusable insights from prior trajectories, making retrieval increasingly important for turning accumulated experience into actionable guidance. At each…
Scaffold-Mediated Post-Training: Co-Evolving Model Parameters and Procedural Scaffold Graphs
arXiv:2608.05156v1 Announce Type: new Abstract: Post-training of large language models optimizes only parameters, while inference-time procedural scaffolds are typically designed independently of parameter training. This disconnect…
Objects as Audio-Visual Modal Sound Fields
arXiv:2608.05145v2 Announce Type: replace Abstract: While modern 3D reconstruction excels at modeling object geometry and appearance, it largely ignores the rich acoustic cues revealed through physical…
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
arXiv:2607.04884v2 Announce Type: replace Abstract: We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, information extraction, text-image translation, and multi-image…
Disentangling 3D Modeling from Spatial Reasoning
arXiv:2608.05242v1 Announce Type: new Abstract: In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning, rather than jointly…
Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution
arXiv:2608.05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long…
Handling Missing Data in Probabilistic Regression Trees
arXiv:2608.06195v1 Announce Type: new Abstract: Probabilistic Regression Trees (PRTrees) are a smooth and consistent alternative to classical regression trees, producing continuous predictions through probabilistic split assignments.…
Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
arXiv:2509.24882v3 Announce Type: replace-cross Abstract: Neural scaling laws underlie many of the recent advances in deep learning, yet their theoretical understanding remains largely confined to linear…
Small Foundation Models of Human Cognition and Behaviour
arXiv:2608.05224v1 Announce Type: new Abstract: Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether…