Coherence-Oriented Dream Scene Visualisation
arXiv:2608.05233v1 Announce Type: new Abstract: Dreams can be emotionally intense but difficult to communicate. We describe the Dream Scene Visualiser (DSV) system which turns written dream…
Papers 5180 stories
Where Privacy Risk Lives in English-Source Multilingual RAG: A Stage-Decomposed Audit Across Five Query Languages
arXiv:2608.05163v1 Announce Type: new Abstract: A common assumption holds that switching to a non-English language makes a multilingual RAG system easier to attack for personal information.…
In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion
arXiv:2608.05237v1 Announce Type: new Abstract: Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the…
Deterministic World Models for Closed-loop Reachability Analysis of End-to-End Vision-based Control
arXiv:2512.08991v3 Announce Type: replace-cross Abstract: End-to-end image controllers that map raw camera frames directly to control actions are increasingly deployed in safety-critical systems. However, formally verifying…
Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
arXiv:2608.06250v1 Announce Type: cross Abstract: In overparameterised classification, training data can be linearly separable even when the underlying distribution is not. In this setting, gradient descent…
Worst-Case Distance-Aware Error Bounds for Neural Networks
arXiv:2510.22021v3 Announce Type: replace-cross Abstract: Safety-critical applications of machine learning require uncertainty estimates that support reliable worst-case analysis. Neural networks (NNs) provide expressive function approximation, while…
The Loss Does Not See the Basis, but Adam Does
arXiv:2608.05136v1 Announce Type: cross Abstract: Gradient descent on a factored model $W = UV^top$ is implicitly biased toward low-rank solutions, while Adam, starting from the same…
Abstract Event Causal Rules: Induction and Application
arXiv:2608.05205v1 Announce Type: new Abstract: Event-centric intelligent analytical systems heavily depend on explicit causal event knowledge for risk early warning, decision-making support and narrative comprehension. Nevertheless,…
Predicting Social Media User Actions: A Hybrid Approach for Common and Rare Behavior Prediction on Bluesky
arXiv:2511.17241v2 Announce Type: replace Abstract: Understanding and predicting user behavior on social media platforms is crucial for content recommendation and platform design. While existing approaches focus…
Token-Native Storage: Read and Write in your Agent's Language
arXiv:2608.02376v2 Announce Type: replace-cross Abstract: Search and database engines still store text as UTF-8, a format built for humans. But the systems that increasingly read and…
NeuroAdaptTrainer: A Fiji/ImageJ Plugin for YOLO-Based Neuron Segmentation, InteractiveCorrection and Transfer Learning
arXiv:2608.05226v1 Announce Type: new Abstract: Neuron counting and segmentation in microscopy images of neuronal cultures is a routine and time-consuming task in neuroscience research, traditionally performed…
All-Quadrant Bounded Clipping GRPO: Closing the Unbounded Blind Spot for Stable and Generalizable Training
arXiv:2601.03895v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) has emerged as a popular algorithm for reinforcement learning with large language models (LLMs). However, GRPO…
Rectifying Geometric Misalignment: Online Source-Free Adaptation for Class-Imbalanced EEG
arXiv:2608.05315v1 Announce Type: new Abstract: Electroencephalography (EEG) based Brain-Computer Interfaces (BCIs) often require unsupervised domain adaptation (UDA) to generalize across subjects and sessions. While Riemannian alignment…
MoCA: Multi-modal Cross-masked Autoencoder for Time Series in Digital Health
arXiv:2506.02260v5 Announce Type: replace Abstract: Wearable devices enable continuous multi-modal physiological and behavioral monitoring, yet analysis of these data streams faces fundamental challenges including the lack…
Learning Latent Memory States from Longitudinal Athlete Monitoring Data
arXiv:2608.06290v1 Announce Type: cross Abstract: We propose a new unit of analysis for longitudinal data: the Latent Memory Table. The scientific contribution is not the encoder.…
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
Training large language model agents for long-horizon tool use typically relies on interactions with real or synthesized executable environments, whose construction and verification are costly, or…
SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding
Understanding 3D scenes is fundamental to embodied intelligence, requiring joint reasoning over heterogeneous information from multiple modalities, including visual and geometric cues. However, the relevance of…
CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal…
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Reinforcement learning (RL) with verifiable rewards constructs trajectory-level advantage estimates, yet it often fails to credit the few pivotal decisions that determine outcomes in long-horizon, multi-turn…
WorldClaw: Agentic 3D Open-World Generation at Scale
Generating large-scale, freely explorable 3D worlds from open-ended text remains challenging because a system must jointly maintain global spatial coherence, rich local content, and explicit assets…
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?
Spatial intelligence is fundamental to embodied agents, yet existing benchmarks focus on local spatial perception from single or few viewpoints, overlooking global spatial awareness over continuous,…
On-Policy Delta Distillation for Multilingual Math Reasoning
On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingual settings remains underexplored. We study OPD…
Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval
Unified multimodal retrieval aims to identify candidates that satisfy complex user intent expressed through heterogeneous inputs. Although Large Vision-Language Model (LVLM)-based retrievers are efficient and scalable,…
ChronoVision: Temporal Reasoning via Latent State Reconstruction
Multimodal large language models excel at passive perception but struggle with complex visual cognitive tasks requiring multi-step temporal reasoning. This degradation largely stems from the inherent…