Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a subtle but consequential attack surface. We study Stealth Pretraining Seeding (SPS), a threat model in which adversaries distribute small amounts of poisoned content across stealth w...
Harsh Kumar, Rahul Maity, Tanmay Joshi et al.· 0 citations
Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously successful policy is retained, it may no longer provide a reliable starting point...
Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its architecture by analyzing the publicly available source code and comparing it with two independent open-source AI agent systems, OpenClaw and Hermes Agent, that answe...
Jiacheng Liu, Xiaohan Zhao, Xinyi Shang et al.· 0 citations
While decoupled control schemes for legged mobile manipulators have shown robustness, learning holistic whole-body control policies for tracking global end-effector poses remains fragile against Out-of-Distribution (OOD) inputs induced by sensor noise or infeasible user commands. To improve robustness against these per...
Ziyang Cheng, Haoyu Wei, Hang Yin et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers can be checked automatically and converted into reliable training signals. Most such pipelines optimize outcome correctness only, which yields sparse feedback for long, mu...
Mohammad Rezaei, Jens Lehmann, Sahar Vahdati· 0 citations
Recent agentic systems demonstrate that large language models can generate complex codebases from natural language prompts. Despite this progress, they present reliability concerns for scientific visualization due to invalid operations, subtle errors, and failure to resolve underspecified inputs. These challenges are c...
Nathaniel Gorski, Shusen Liu, Bei Wang· 0 citations
The results demonstrate that similarity-based representation learning combined with density-based aggregation is a promising alternative to object-centric approaches for point cloud segmentation in highly granular detectors.
Max Marriott-Clarke, Lazar Novakovic, Elizabeth Ratzer et al.· PRX Intelligence· 1 citation
While Reinforcement Learning (RL) enhances Large Language Model reasoning, on-policy algorithms like GRPO are sample-inefficient as they discard past rollouts. Existing experience replay methods address this by reusing accurate samples for direct policy updates, but this can incur additional storage costs and concentra...
Long Li, Zhijian Zhou, Tianyi Wang et al.· 0 citations
In this paper, we present a novel learning framework for finding shortest paths in graphs utilizing Generative Flow Networks (GFlowNets). First, we examine theoretical properties of GFlowNets in non-acyclic environments in relation to shortest paths. We prove that, if the total flow is minimized, forward and backward p...
Nikita Morozov, Ian Maksimov, Daniil Tiapkin et al.· 0 citations
Edge classification on directed dynamic graphs is critical for understanding evolving user-item interactions and behavioral patterns in recommender systems and social platforms. Existing dynamic graph architectures typically process these interactions using shared parameters for nodes with semantically distinct roles,...
Pass@$k$ is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-answer reasoning. It defines success if any of $k$ independently sampled solutions passes a verifier. This multi-sample inference metric has motivated inference-aware fine...
Anas Barakat, Souradip Chakraborty, Khushbu Pahwa et al.· 0 citations
Delayed generalization, where training accuracy becomes nearly perfect substantially before test accuracy, has often been studied in the context of the depth and compositional structure of deep networks. In this paper, we ask whether delayed generalization can occur in simpler settings. We show that it can arise in a l...
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 27, 2026
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
