MLINFO COLLECTION
Benchmarking in reinforcement learning is usually relative: algorithms are ranked by returns on environments with unknown optima. Distance to optimality remains unobservable, while conclusions may…
Sparse attention reads only a small subset of the key-value cache, and how to treat the unread tail remains a key challenge. Discarding the tail biases the output, and sampling it as previous…
We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activated). IQuest-Q1 is developed through a three-stage process: (1) stable and…
Random projections (RP) offer an effective method for reducing computational and storage overhead while preserving the geometric structure of data. However, existing studies have primarily focused on…
Sub-hourly dispatch, balancing, and storage control increasingly depend on forecasts that anticipate rapid variability in solar generation. Accurate sky-image-based irradiance forecasting requires a…
General-purpose embeddings trained on profile similarity often misrank candidates in professional networks, where relevance is inherently complementary rather than symmetric. For example, job seekers…
Accurate estimation of diffuse horizontal irradiance (DHI) is critical for optimising photovoltaic system performance and energy forecasting yet remains challenging in regions lacking comprehensive…
Just as different languages express the same concept through different words, neural networks express similar functions through incompatible coordinate systems. Different architectures, random…
Activation verbalizers translate the internal representations of large language models into human-readable text. The recently proposed natural language autoencoders (NLAs) learn this by…
Auxiliary patient data can improve chest X-ray report generation, but directly concatenating heterogeneous clinical information with visual tokens produces long, variable-length decoder prompts and…
Cinematic video generation requires both temporal inference from limited inputs (i.e., sparse rather than frame-by-frame guidance) and factor-aware control of character, scene, action, and camera.…
Diffusion language models (DLMs) decode multiple tokens in parallel, so individually valid tokens can be incompatible together under a schema. Exact joint inference over a grammar graph enforces…
Large language models (LLMs) can translate natural-language optimization problems into solver programs, but reliably producing correct formulations and implementations remains challenging. Existing…
Despite recent advances, deepfake detectors remain vulnerable to adversarial examples, particularly in diverse, real-world settings. We propose MIG-COW, a novel adversarial attack framework that…
Vision-language models (VLMs) struggle with in context learning compared to their textual counterparts. Our preliminary study shows that VLMs rely on textual shortcuts and underutilize the visual…
Neurosurgical navigation commonly presents magnetic resonance imaging (MRI) as 2D slices, making it difficult to relate the anatomy in those slices to the cortical surface observed through the…
Chemical AI workflows routinely represent the same molecule through multiple co-referring identifiers, including trivial names, IUPAC names, and SMILES, implicitly assuming that these representations…
Population graph learning supports brain disorder diagnosis by sharing information across subjects. Its effectiveness, however, depends on whether the relationships guiding this exchange are relevant…
Active inference casts perception, learning and planning as variational inference, where the Expected Free Energy (EFE) defines the planning objective. Recent work showed that EFE minimization can be…
Deep Gaussian processes (DGPs) are appealing Bayesian regression models, but their standard discrete-depth parameterization often becomes harder to optimize as depth grows. We argue that depth is…
PowerPoint presentations (PPTs) are a dominant medium for communication across diverse domains, yet high-quality PPT generation still depends heavily on labor-intensive human effort. Recent advances…
Large language models trained on data generated by other models can sometimes inherit traits unrelated to that data, a phenomenon called subliminal learning. We study both hard label distillation,…
On-policy self-distillation (OPSD) improves reasoning by training a model on its own trajectories with dense token-level supervision from a privileged copy conditioned on a reference solution.…
Fine-tuning has become a common way to customize text-to-image models, leading to community collections of over 100K lightweight adapters. Adapters sharing a base model can be merged with continuous…