MLINFO COLLECTION
While functional magnetic resonance imaging (fMRI) decoders reconstruct images and 3D objects, recovering the metric geometry of rooms from a moving viewpoint remains an open challenge. We introduce,…
We present DeepOpen, a decision-Oriented intent-classification framework with dataset- specific systems for BANKING77 and CLINC150. On BANKING77, a single English classi- fier continued with…
Reward models score responses for preference optimization, filtering and ranking, and pooling scores across prompts needs them to be comparable. Yet pairwise evaluation compares two responses to the…
Modern transformers often solve complex tasks by generating and refining intermediate reasoning steps. To develop a theoretical understanding of chain-of-thought (CoT) reasoning, a notable recent…
Text-to-music alignment is commonly evaluated by the global similarity between text and audio embeddings, which collapses all described attributes into a single score and obscures which ones are…
Policy enforcement for LLM agents has shifted from single-turn content moderation to compound, application-specific policies evaluated over multi-turn transcripts and tool-call trajectories.…
As large language models are deployed in high-stakes roles such as therapy, education, and personal assistance, their social cognition must be assessed reliably. Current Theory of Mind (ToM)…
While reasoning traces improve model capability, they also provide supervision signals for downstream distillation. Initial efforts to mitigate this issue rely on decoding-time interventions, but…
Generative artificial intelligence promises to democratize personalized tutoring, yet the longitudinal stability of adaptive systems remains under-theorized. Current ethical discourse focuses on…
Generative video compression (GVC) methods usually employ decoder-side diffusion models to denoise reconstructed signals based on generative priors. Besides, most of these methods perform denoising…
Decision support has become sophisticated at exploring uncertainty, but much less so at representing the architecture of the decision itself. As a result, the decision space is often narrowed before…
Efficient custom operators are essential for modern deep learning workloads, yet developing high-performance kernels for Ascend NPUs remains slow, expert-intensive, and difficult to automate.…
Natural-language interfaces allow users to command robotic systems without interacting directly with mission planners or robotics middleware. Their reliable use depends on robot tool routing, defined…
Capability benchmarks measure what large language models can do, but not whether their recommendations remain appropriate as decision conditions change. This paper proposes a trajectory-based…
End-to-end control policies trained via Reinforcement Learning (RL) have emerged as an alternative to conventional surgical robotic control approaches, with recent studies exploring state-based…
Generative AI assistants are becoming an advertising medium, embedding sponsored content in their answers. This setting departs from classical position auctions in two ways: an ad's click-through…
Robot demonstrations record what the robot saw and what it did. They do not specify how the 3D world changed in between.
Robust manipulation of soft objects, such as garments, is a critical skill for service and household robots to adopt, but remains challenging due to its high-dimensional state space, and…
Generative modeling for Computer-Aided Design (CAD) remains fundamentally challenged by the need to capture the intricate interplay between discrete topological connectivity and precise spatial…
Soil moisture and temperature govern plant-water availability and microbial activity, making them key indicators for evaluating land-restoration efforts on degraded landscapes. However, the physical…
Many language-model pipelines end in a closed-set decision, such as selecting a tool. Prompting a large language model for it is slow and order-sensitive.
AI models, and time-series models in particular are typically ranked by accuracy and deployed under constraints absent from that ranking. In this paper, we study a real setting where these…
Detecting online social engineering (SE) scams often requires examining website workflows, verifying claims against external sources, and connecting evidence across multiple pages. Existing detectors…
Assistive devices for patients with neurodegenerative movement disorders must combine high mechanical transparency with the ability to generate corrective interaction forces. Achieving both…