ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models
Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independently of whether that context is relevant, true,…
Latest
Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices
Real-time EEG classification on edge devices is bottlenecked by the floating-point arithmetic of conventional neural networks. We investigated Differentiable Logic Gate Networks (Diff-Logic) as a hardware-native…
Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation
Text-to-video generation has advanced significantly over the past five years through scaling of model size, data, and compute. Unlike model architecture, training data is often underexplored.…
SLAM in Low-Light Environments: Project Report
Simultaneous localization and mapping (SLAM) is one of the fundamental problems in robotics, as it enables autonomous operations in real-world scenarios. Under low illumination, reduced contrast,…
DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations
As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose AI assistants and automating complex workspace workflows.…
Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models
Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypernetworks provide a promising solution to large-scale knowledge injection. Although…
An Exam for Active Observers
Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have argued…
Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations
Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it. The test is structurally…
FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation
Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in high-resolution video generation. Training-free sparse attention reduces this cost, but adaptive Top-p routing…
Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning
Reinforcement learning with verifiable rewards (RLVR) has substantially improved language-model reasoning, yet its extension to vision-language models remains constrained by the lack of training data that…