Hi all, I don’t know what exactly I’m looking for by posting here but here goes. I’m a final year phd student and my work is in RL based robotic control (broad area, I work on a specific application). Honestly Idk why I picked this topic. Neither my supervisory team nor I had any prior experience. In the start because of my lack of experience my topic seemed doable, then in the middle it seemed like it would […]
arXiv:2603.03407v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong empirical performance across pharmacology and drug discovery tasks, yet the internal mechanisms by which they encode pharmacological knowledge remain poorly understood. In this work, we investigate how drug-group semantics are represented and retrieved within Llama-based biomedical language models using causal and probing-based interpretability methods. We apply activation patching to localize where drug-group information is stored across model layers and token positions, and complement this analysis with […]
arXiv:2601.22249v1 Announce Type: new Abstract: Code generation is a core application of large language models (LLMs), yet LLMs still frequently fail on complex programming tasks. Given its success in mathematical reasoning, test-time scaling approaches such as Process Reward Model (PRM)-based Best-of-N selection offer a promising way to improve performance. However, existing PRMs remain ineffective for code generation due to the lack of meaningful step decomposition in code and the noise of Monte Carlo-estimated partial-solution correctness scores (rewards). To […]
Federated Learning (FL) enables distributed Artificial Intelligence (AI) across cloud-edge environments by allowing collaborative model training without centralizing data. In cross-device deployments, FL systems face strict communication and participation constraints, as well as strong non-independent and identically distributed (non-IID) data that degrades convergence and model quality. Since only a subset of devices (a.k.a clients) can participate per training round, intelligent client selection becomes a key systems challenge. This paper proposes FedLECC (Federated Learning with Enhanced Cluster Choice), a […]
Amazon builds first foundation model for multirobot coordination Trained on millions of hours of data from Amazon fulfillment centers and sortation centers, Amazons new DeepFleet models predict future traffic patterns for fleets of mobile robots. Robotics Joey Durham August 11, 11:00 AM August 13, 11:05 AM Large language models and other foundation models have introduced a new paradigm in AI: large models trained in a self-supervised fashion no data annotation required on huge volumes of data can learn […]
Amazon is developing a new smartphone over a decade after discontinuing the Fire Phone, Reuters reported today, citing four anonymous “people familiar with the matter.” Reuters said the phone is codenamed Transformer but couldn’t confirm what it might cost, how much Amazon has invested into development thus far, or how much Amazon expects to make off the device. Like any product reportedly under development, it’s possible that Amazon will never release the phone. Reuters’ sources noted that Transformer […]
Introducing Chronos-2: From univariate to universal forecasting In-context learning enables a model that can solve forecasting tasks with an arbitrary number of dimensions in a zero-shot manner. Machine learning Abdul Fatir Ansari Oleksandr Shchur Jaris Kken October 20, 09:53 AM January 06, 09:54 AM Time series forecasting is crucial to numerous applications in business, science, and engineering. Recently, foundation models have led to a paradigm shift in time series forecasting. Unlike statistical models, which extrapolate from a single […]
arXiv:2602.20342v1 Announce Type: new Abstract: In this study, we present an end-to-end pipeline capable of converting drone-captured video streams into high-fidelity 3D reconstructions with minimal latency. Unmanned aerial vehicles (UAVs) are extensively used in aerial real-time perception applications. Moreover, recent advances in 3D Gaussian Splatting (3DGS) have demonstrated significant potential for real-time neural rendering. However, their integration into end-to-end UAV-based reconstruction and visualization systems remains underexplored. Our goal is to propose an efficient architecture that combines live video […]
The accepted papers at ICML have been published. ICML is a top Machine Learning conference, and one of the most relevant to Deep Learning, although NIPS has a longer DL tradition and ICLR, being more focused, has a much higher DL density. Most mentioned institutions I thought it would be fun to compute some stats on institutions. Armed with Jupyter Notebook and regex, we look for all of the institution mentions, add up their counts and sort. Modulo a […]