MLINFO COLLECTION
Discretizing continuous actions into discrete skills using methods like VQ-VAE has emerged as a powerful paradigm for robotic manipulation. However, quantization errors yield a suboptimal…
Visual foundation models learn rich pathological morphology but lack explicit concept-level supervision. Vision--language pretraining can provide this supervision but requires costly image--text…
Perception tasks for navigation in robotics, including aerial platforms such as drones and autonomous driving systems, are inherently structured. Drone-mounted cameras typically capture sky above,…
Reliable detection of large language model (LLM)-generated text must remain effective under meaning-preserving text revisions, such as rewriting, polishing, and expansion. In practice, LLM outputs…
Football action valuation estimates players' contributions to future scoring. Existing multi-agent deep reinforcement learning (MADRL) models use 2D positions and velocities, omitting posture…
Large vision-language models (LVLMs) represent images and videos as long visual-token sequences, substantially increasing inference costs. These costs motivate visual-token pruning, whose…
Time-series forecasters are ranked almost entirely by accuracy metrics, but a forecast's decision value, its effect on the downstream decision, need not track accuracy and is rarely measured. This…
Compositional diffusion planners have demonstrated remarkable success on long-horizon diffusion planning by sampling short trajectories, namely chunks, and composing them into a long trajectory.…
Vision Transformers (ViTs) achieve strong image recognition performance, but their self-attention increases quadratically with the number of input tokens and makes them computationally expensive. The…
Feed-forward 3D Gaussian Splatting has recently emerged as a promising alternative to per-scene optimization, enabling fast novel view synthesis by predicting Gaussian primitives directly from input…
Text summarization is an important task for advancing natural language processing (NLP) research and applications in Indic languages. Despite progress in extractive and abstractive summarization,…
Topology-agnostic motion generation aims to synthesize motions for diverse characters with arbitrary skeletons. Unlike conventional motion generation, which assumes a fixed skeletal template, this…
We study adversarial linear bandits with strong corruption, in which an adaptive adversary chooses the reward vectors and a strong adversary corrupts each observed reward after seeing the learner's…
Mobile manipulator robots rarely reposition their base during manipulation, because doing so requires real-time knowledge of how well the arm can reach its surroundings among obstacles. Reachability…
Robot imitation learning uses demonstrations from operators of varying skill, but selecting training data remains challenging. Existing methods score demonstrations using smoothness, diversity, or…
Kernel methods face two recurrent bottlenecks: the cubic cost of inverting an $n\times n$ kernel matrix, as in kernel ridge regression, and the evaluation of kernel integrals, as required in kernel…
Behavior Cloning has demonstrated promising generalization capabilities for robotic manipulation in terrestrial environments. However, marine visual distortions and dynamic currents create a severe…
Whole-prompt translation evaluates a request in different languages but does not compare which component carries a language. We introduce a paired reversal: translate the complete request component…
On-policy distillation (OPD) trains a student on its own responses using token-level feedback from a teacher. As responses grow longer, the student's prefix can depart from the teacher's own…
Many problems in computational statistics and machine learning can be formulated as approximating a target distribution by minimizing a discrepancy over a restricted class of candidate distributions.…
We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic…
Model distillation has become a major concern in the rapidly growing generative AI discourse. In its simplest form, distillation is the phenomenon where smaller firms can use data distilled from…
Discrete visual tokens represent vision in a discrete form analogous to language, offering a native interface for multimodal modeling under a shared next-token prediction objective. However,…
Interactive world generation requires models to follow successive commands while preserving relevant history and action consequences. We present Hy-Nomas, a video world model with an 8B diffusion…