February 2026

Continual Learning (CL) with large-scale pre-trained models (PTMs) has recently gained wide attention, shifting the focus from training from scratch to continually adapting PTMs. This has given rise to a promising paradigm: parameter-efficient continual learning (PECL), where task interference is typically mitigated by assigning a task-specific module during training, such as low-rank adapters. However, weight regularization techniques, such as Elastic Weight Consolidation (EWC)-a key strategy in CL-remain underexplored in this new paradigm. In this paper, we revisit weight […]

Ver mais

Training large-scale generative models is resource-intensive and relies heavily on heuristic dataset weighting. We address two fundamental questions: Can we train Large Language Models (LLMs) modularly-combining small, domain-specific experts to match monolithic performance-and can we do so robustly for any data mixture, eliminating heuristic tuning? We present a theoretical framework for modular generative modeling where a set of pre-trained experts are combined via a gating mechanism. We define the space of normalized gating functions, $G_{1}$, and formulate the […]

Ver mais

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a trade-off between safety and utility. We introduce a training framework that adapts regularization in response to safety risk, enabling models to remain aligned throughout fine-tuning. To estimate safety risk at training time, we explore two distinct approaches: a judge-based Safety Critic that assigns high-level harm […]

Ver mais

Efficient estimation of causal and structural parameters can be automated using the Riesz representation theorem and debiased machine learning (DML). We present genriesz, an open-source Python package that implements automatic DML and generalized Riesz regression, a unified framework for estimating Riesz representers by minimizing empirical Bregman divergences. This framework includes covariate balancing, nearest-neighbor matching, calibrated estimation, and density ratio estimation as special cases. A key design principle of the package is automatic regressor balancing (ARB): given a Bregman […]

Ver mais

Robotic camera systems enable dynamic, repeatable motion beyond human capabilities, yet their adoption remains limited by the high cost and operational complexity of industrial-grade platforms. We present the Intelligent Robotic Imaging System (IRIS), a task-specific 6-DOF manipulator designed for autonomous, learning-driven cinematic motion control. IRIS integrates a lightweight, fully 3D-printed hardware design with a goal-conditioned visuomotor imitation learning framework based on Action Chunking with Transformers (ACT). The system learns object-aware and perceptually smooth camera trajectories directly from human […]

Ver mais

Hi. I am an undergrad (school of 2027), greatly interested in RL. I came across RL in the second year of my undergrad, and it greatly fascinated me. I will be starting off with the RL courses (online ofc) from the next semester (currently studying Deep Learning). As I want to become a Research Scientist in the future, I want to know how to prepare along my courses to surely get an MS (Research) or PhD abroad (in […]

Ver mais

Learning from self-sampled data and sparse environmental feedback remains a fundamental challenge in training self-evolving agents. Temporal credit assignment mitigates this issue by transforming sparse feedback into dense supervision signals. However, previous approaches typically depend on learning task-specific value functions for credit assignment, which suffer from poor sample efficiency and limited generalization. In this work, we propose to leverage pretrained knowledge from large language models (LLMs) to transform sparse rewards into dense training signals (i.e., the advantage function) […]

Ver mais

We develop a method for training neural networks on Boolean data in which the values at all nodes are strictly $pm 1$, and the resulting models are typically equivalent to networks whose nonzero weights are also $pm 1$. The method replaces loss minimization with a nonconvex constraint formulation. Each node implements a Boolean threshold function (BTF), and training is expressed through a divide-and-concur decomposition into two complementary constraints: one enforces local BTF consistency between inputs, weights, and output; […]

Ver mais