MLINFO COLLECTION
Spiking Neural Networks (SNNs) promise energy-efficient inference through sparse, event-driven computation, yet remain constrained on continuous, context-dependent tasks such as automatic speech…
Backpropagation remains the dominant training paradigm, using backward gradients and local updates that can suffer from vanishing or exploding gradients in deep networks. Although the Forward-Forward…
During steady pouring, images and robot pose may remain nearly unchanged while transferred mass accumulates, making the return decision ambiguous for a whole-task vision-language-action (VLA) policy.…
Generative image compression (GIC) delivers strong perceptual quality at low bitrates. However, GIC methods with strong perceptual quality often rely on pretrained diffusion models with high latency,…
Learning motion planning policies that remain reliable under closed-loop execution is a central challenge in Autonomous Driving (AD). Imitation Learning (IL) scales well to large AD datasets but…
Mixture-of-Experts (MoE) architectures scale model capacity efficiently, yet their substantial memory footprint poses a major barrier to deployment. Expert pruning reduces this footprint, but most…
The deployment of small and quantized language models in resource-constrained settings raises an important fairness question: when a compressed model produces fewer biased responses, does this…
Text-to-Image models reproduce societal stereotypes, and existing mitigation applies one demographic correction to the whole scene. In multi-person scene generation this creates a trade-off: global…
Video anomaly detection (VAD) is a challenging task for surveillance systems due to the scarcity and diversity of anomalous events. While semi-supervised VAD approaches have advanced the field, many…
Digital image transmission typically optimizes source coding, channel coding, and modulation separately, limiting how source representations adapt to channel impairments. We propose SemQAM, a joint…
Object detection models for autonomous driving commonly experience substantial performance drops when deployed under adverse weather due to the domain shift between training data and real-world…
Edge medical segmentation must reconcile small model size, high accuracy, and fast inference. TernScope addresses this tradeoff through model--hardware co-design, learning a compact segmentation…
Early diagnosis of hepatocellular carcinoma is critical to preserve access to curative treatment options. The Liver Imaging Reporting and Data System (LI-RADS) provides a standardized framework for…
Perceptive locomotion policies typically observe a dense robot-centric elevation map, although only the terrain beneath and around the next footsteps informs the control decision. Learned encoders…
Iris recognition systems are vulnerable to presentation attacks (PAs), including textured contact lenses, print replays, and synthetic irises. Existing PAD methods rely on supervised learning with…
Deep neural networks deployed on smart glasses must adapt to changes in the distribution of incoming data while adhering to strict privacy and device constraints. We present No Frames, Just…
In this paper, we study quantile distributional policy evaluation, where the return distribution under a given policy is approximated by the quantile Bellman fixed point $\bmη_m$. We investigate the…
Graph neural networks (GNNs) are among the standard tools for molecular property prediction, but the atom-level explanations of their predictions are hard for medicinal chemists to act on. We propose…
Legged robots can extend planetary exploration to rugged and discontinuous terrain that is inaccessible to conventional rovers. In lunar gravity, jumping further expands this mobility by enabling…
We consider online prediction from experts, a fundamental problem in machine learning, under differential privacy constraints. Existing private algorithms achieve near-optimal regret…
Teleoperation enables intuitive control of remote engineering robots for precision tasks. Existing direct joint-mapping methods have two limitations: independent motor saturation disrupts pitch-roll…
Linear-attention language models keep their context in a recurrent state of fixed size, where an inference system stores one copy of this state for every sequence it decodes at the same time. Storing…
Speculative decoding accelerates large language model inference by employing a compact draft model to propose candidate tokens that are verified in parallel by a target model. Conventional training…
In this report, we introduce pplx-embed-v2-late, a pair of 0.6B and 9B multilingual and multimodal late-interaction models. Both models achieve state-of-the-art results within their respective size…