MLINFO COLLECTION
Reusable skills allow large language model agents to package task-specific procedures, tool affordances, and execution guidance into modular units. Prior work has largely studied how agents retrieve,…
Point cloud transformers aim to capture detailed local geometry and relationships across a scene at a manageable computational cost. Two common approaches are window attention and global attention.
When a user says "Keep it short", how short should the LLM's response be? More generally, users and applications require different levels of instruction adherence, but prompting does not reliably…
A conventional embodied agent in an indoor environment builds a map by accumulating noisy real-world measurements and results from heavy inference to guide navigation. While the detailed measurements…
Agentic robot systems combine language-model reasoning with robot policies to monitor execution and recover from failures. However, reviewing every action chunk incurs substantial overhead, even in…
Recent advances in specialized decision models have expanded the possibilities for zero-shot classification, yet their effectiveness on Vietnamese remains underexplored. This study evaluates four…
Looped and depth-grown language models reuse computations across depth and have attracted interest for their reasoning capabilities. Building on prior suggestive evidence of improved…
The interpretability of complex neural networks remains a critical challenge, especially for models already deployed in high-stakes domains. To address this, we adapted the Feature Selection Layer…
Code-switched (CS) automatic speech recognition (ASR) remains difficult because real CS speech is scarce and synthetic speech does not fully match it. We investigate whether synthetic CS speech is…
With the growth of scientific output, the peer review system is approaching a breaking point: reviewers are increasingly hard to secure, and turnaround times lengthen accordingly. LLM-assisted or…
Vector quantization (VQ), in particular lattice-based methods, offer strong rate-distortion trade-offs for low-bit large language models (LLMs), yet their behavior under quantization-aware training…
Multilingual language models can give different identity judgments when the same people's names are written in different scripts. We study this effect using 601 audited identity pairs with attested…
Continual learning requires a model to keep acquiring new skills and knowledge without compromising its existing capabilities. Parametric methods suffer from catastrophic forgetting and loss of…
Bashkir is a low-resource agglutinative language written in Cyrillic and remains poorly represented in modern LLMs. We present an open resource suite and a systematic benchmark of adaptation methods:…
Equilibrium neural networks define their hidden state as the fixed point of a contraction, so their effective depth is set at evaluation time rather than by the architecture. Using them for fully…
Estimating propeller rates from a moving event camera requires separating blade rotation from the changing image geometry. Background activity mixes with blade events, while repeated blade…
Robotic swarms must coordinate across diverse missions, yet existing controllers often require redesign, retuning, or retraining when objectives change. Here we show that probabilistic energy…
Communicating with the public during an emergency entails issuing warning messages promptly. In Europe, it often requires producing them in more than one language.
Collective ordering in correlated electron systems emerges from microscopic dynamics, yet the evolution of observable textures need not admit a closed, memoryless description. We introduce a…
Probabilistic computing has proved useful for combinatorial optimization, but conventional implementations rely on binary stochastic units and sigmoid-based updates. Extending these systems to…
Vision and touch provide complementary cues for object pose and local contact geometry, but external cameras are often occluded at the contact site. We present GelSlim 5.0, a fingertip sensor that…
Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception. In this report, we present WeVisOne-VL (WeChat Vision All-in-One), a powerful VLM that unifies…
Finite element model updating is among the most general approaches to discover constitutive models from structural experiments: since the displacement field is computed rather than measured, it…
Local feature matching is typically formulated for image pairs, although structure-from-motion and visual localization commonly match one reference image against many retrieved or covisible…