RECAP (Robust Safety Alignment via Counter-Aligned Prefilling), a principled reinforcement learning (RL) method for post-training that explicitly teaches models to override flawed reasoning trajectories and reroute to safe and helpful responses, substantially improves safety and jailbreak robustness, reduces overrefusal, and preserves core reasoning capability.
Sheng-Hsuan Peng, E. Smith, Ivan Evtimov et al.· arXiv.org· 10 citations· ⚡2
This work demonstrates that a low-rank structure naturally emerges in the shifted successor measure, which captures the system dynamics after bypassing a few initial transitions, and establishes a connection between the necessary shift and the local mixing properties of the underlying dynamical system, which provides a natural way of selecting the shift.
Bastien Dubail, Stefan Stojanovic, Alexandre Proutière· Neural Information Processin...· 4 citations· ⚡1
The results demonstrate that SOM-based statistical replay offers a scalable, label-free, exemplar-free approach to class-incremental continual learning under standard task-boundary protocols.
Pujan Thapa, Alexander G. Ororbia, Travis J. Desell· 0 citations
Experiments show that RegCL achieves strong retention and adaptation under domain-incremental learning, outperforming competitive non-replay continual learning and merging baselines, suggesting that RegCL can serve as a compact visual adaptation component for evolving multi-sensorial media pipelines.
Yuan-Chen Shu, Zhiwei Lin, Xiaoyu Zhou et al.· 2 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
The EXPonential-weight algorithm for prompt Optimization} (EXPO) is proposed to automatically optimize the task description and meta-instruction in the meta-prompt for LLM-based agents and is extended to additionally optimize the exemplars (i.e., history of interactions) in the meta-prompt to further enhance the performance, hence introducing the EXPO-ES algorithm.
Ming-Ze Kong, Zhiyong Wang, Yao Shu et al.· arXiv.org· 7 citations
Amortized sampling of the posterior over data is studied, and the asymptotic correctness of a data-free learning objective, relative trajectory balance, is proved for training a diffusion model that samples from this posterior, a problem that existing methods solve only approximately or in restricted cases.
S. Venkatraman, Moksh Jain, Luca Scimeca et al.· Neural Information Processin...· 75 citations· ⚡5
This work benchmarks several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods (continuous generative flow networks), and proposes a novel exploration strategy for off-policy methods, based on local search in the target space with the use of a replay buffer.
Marcin Sendera, Minsu Kim, Sarthak Mittal et al.· Neural Information Processin...· 52 citations· ⚡7
Expected Goals (xG) has emerged as a popular tool for evaluating finishing skill in soccer analytics. It involves comparing a player's cumulative xG with their actual goal output, where consistent overperformance indicates strong finishing ability. However, the assessment of finishing skill in soccer using xG remains contentious due to players'difficulty in consistently outperforming their cumulative xG. In this paper, we aim to address the limitations and nuances surrounding the evaluation of finishing skill using xG statistics. Specifically, we explore three hypotheses: (1) the deviation between actual and expected goals is an inadequate metric due to the high variance of shot outcomes and limited sample sizes, (2) the inclusion of all shots in cumulative xG calculation may be inappropriate, and (3) xG models contain biases arising from interdependencies in the data that affect skill measurement. We found that sustained overperformance of cumulative xG requires both high shot volumes and exceptional finishing, including all shot types can obscure the finishing ability of proficient strikers, and that there is a persistent bias that makes the actual and expected goals closer for excellent finishers than it really is. Overall, our analysis indicates that we need more nuanced quantitative approaches for investigating a player's finishing ability, which we achieved using a technique from AI fairness to learn an xG model that is calibrated for multiple subgroups of players. As a concrete use case, we show that (1) the standard biased xG model underestimates Messi's GAX by 17% and (2) Messi's GAX is 27% higher than the typical elite high-shot-volume attacker, indicating that Messi is even a more exceptional finisher than people commonly believed.
This paper proposes a method to approximate the joint posterior over not only the structure of a Bayesian Network, but also the parameters of its conditional probability distributions, using a single GFlowNet whose sampling policy follows a two-phase process.
T. Deleu, Mizu Nishikawa-Toomey, Jithendaraa Subramanian et al.· Neural Information Processin...· 65 citations· ⚡4
The possibility of inferring high-dimensional data inference in a model that consists of a prior and an auxiliary differentiable constraint given some additional information is considered, thereby allowing a range of potential applications in adapting models to new domains and tasks.
Alexandros Graikos, Esmeralda S. Whitammer, N. Jojic et al.· Neural Information Processin...· 316 citations· ⚡15
It is proved that any global minimizer of the trajectory balance objective can define a policy that samples exactly from the target distribution, and empirically demonstrate the benefits of the trajectories balance objective for GFlowNet convergence, diversity of generated samples, and robustness to long action sequences and large action spaces.
Esmeralda S. Whitammer, Moksh Jain, Emmanuel Bengio et al.· Neural Information Processin...· 302 citations· ⚡60
We study the mixing time of weighted Dikin walks for sampling from exponential distributions on polytopes and truncated positive-semidefinite (PSD) cones. Our first result gives a general total-variation mixing bound under strong self-concordance, $\bar{\nu}$-symmetry, and mixed-trace regularity on the local metric. The key idea is to control the Metropolis--Hastings acceptance probability on a high-probability region rather than at every point. Applying this framework to the Lee--Sidford, Lewis-weight, and John metrics yields an $\widetilde O(d^2)$ mixing bound for sampling from polytopes, while applying it to a hybrid barrier yields an $\widetilde O(d^4)$ mixing bound for sampling from truncated PSD cones. Our second result establishes stronger $\chi^2$-divergence guarantees and pointwise acceptance control using a new fourth-order bootstrap condition. For a suitably scaled Lee--Sidford metric, this yields an $\widetilde O(d^2)$ mixing bound in $\chi^2$-divergence, improving on the previous $\widetilde O(d^{9/4})$ bound.
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
Adaptive AI agents can help make BIM data more machine-readable by navigating IFC models, interpreting inconsistent information, and mapping it to defined standards. In this blog, Alok Rawat shares findings from a real-world pilot in construction workflows. The post Adaptive AI Agents in Construction Workflows appeared first on GPT-Lab.
