Deep generative models (DGMs) have caused a paradigm shift in the field of machine learning, yielding noteworthy advancements in domains such as image synthesis, natural language processing, and other related areas. However, a comprehensive evaluation of these models that effectively captures the interplay among fideli...
Tadeusz Dziarmaga, Marcin K\k{a}dzio{\l}ka, Laura Musio{\l} et al.· 0 citations
Deep Reinforcement Learning (DRL) enables robots to learn complex behaviors through interaction with the environment. However, due to the unrestricted nature of the learning algorithms, the resulting solutions are often brittle and appear unnatural. This is especially true for learning direct joint-level torque control...
Oliver Hausd\"orfer, Alexander von Rohr, \'Eric Lefort et al.· 0 citations
Many optimization problems require balancing multiple conflicting objectives. To generalize gradient descent, which is limited to single-objective optimization, we introduce Jacobian descent (JD) and its stochastic variants. This algorithm iteratively updates parameters using the Jacobian matrix of a vector-valued obje...
Pierre Quinton, Val\'erian Rey· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Behind the general terms like adversarial attacks and generative adversarial networks (GANs), such criteria as AI resilience and AI robustness gained a crucial importance, in trying to make the emergent AI tools reliable, energy-efficient and safe. From mathematical perspective, these problems boil down to finding a ma...
Typhoon, a masking strategy that uses the gradient of the MLM loss with respect to one-hot token inputs to estimate online how much each token type contributes to the objective, is introduced and evaluated against random masking and whole-word masking.
Bruce Changlong Xu, Muhammed Shahir Abdurrahman, Hashem Elezabi· 0 citations
Do visual tasks have a relationship, or are they unrelated? For instance, could having surface normals simplify estimating the depth of an image? Intuition answers these questions positively, implying existence of a structure among visual tasks. Knowing this structure has notable values; it is the concept underlying tr...
Amir Zamir, Alexander Sax, William Shen et al.· 0 citations
A counterfactual evaluation framework that separates selected records (targets) from the applied change (an update) is introduced and four executions combine proposed and reference targets and updates to measure the effects of correcting or retaining each component and their interaction.
Code generation models are increasingly used to produce interactive artifacts, such as websites and user interfaces. Many properties that determine whether these interfaces are useful only become apparent through realistic interaction, making them difficult to incorporate into model training. In this paper, we introduc...
Jiawen Li, Chenming Ge, Alice Gao et al.· 0 citations
Recursive self-improvement (RSI) requires agents to diagnose system bottlenecks and coordinate improvements across training and inference. We refer to the agents' capability to jointly optimize training data, the trainer, and the inference harness as cross-component co-design. We introduce VibeTraining-Bench, a benchma...
Ruotian Peng, Yuanyi Ren, Shuaiqi Liu et al.· 0 citations
In many human-AI systems, candidate actions are not executed directly but are first evaluated by another decision-making entity under a potentially different objective or decision model. Standard decision-theoretic frameworks do not require this interaction to be represented explicitly, as they define transition dynami...
VLA-Rolling is introduced, a lightweight inference framework that reuses action tails through three stages: action-tail inheritance, per-action confidence estimation, and confidence-guided refinement through renoising and denoising budget allocation, while the underlying VLA remains frozen.
Si-Cheng He, Ying-Ying Pan, Qiu-Ting Yu et al.· 0 citations
