相关论文: Revisiting Auxiliary Losses for Conditional Depth …

Mitigating reward hacking--where AI systems misbehave due to flaws or misspecifications in their learning objectives--remains a key challenge in constructing capable and aligned models. We show that we can monitor a frontier reasoning…

Tool-augmented reasoning has become a popular direction for LLM-based agents, and it is widely assumed to improve reasoning and reliability. However, we demonstrate that this consensus does not always hold: in the presence of semantic…

In this case study, we present a data-efficient point cloud segmentation pipeline and training framework for robust segmentation of unimproved roads and seven other classes. Our method employs a two-stage training framework: first, a…

Recently, large language models (LLMs) have demonstrated superior performance across various tasks by adhering to scaling laws, which significantly increase model size. However, the huge computation overhead during inference hinders the…

Wu et al. (2026) showed that most frontier large language models (LLMs) recommend a sponsored, roughly twice-as-expensive flight when their system prompt contains a soft sponsorship cue. We reproduce their evaluation on ten open-weight chat…

Classifying Non-Functional Requirements (NFRs) in software development life cycle is critical. Inspired by the theory of transfer learning, researchers apply powerful pre-trained models for NFR classification. However, full fine-tuning by…

The deployment of autonomous AI agents in derivatives markets has widened a practical gap between static model calibration and realized hedging outcomes. We introduce two reinforcement learning frameworks, a novel Replication Learning of…

Prompt tuning is a parameter-efficient tuning (PETuning) method for utilizing pre-trained models (PTMs) that simply prepends a soft prompt to the input and only optimizes the prompt to adapt PTMs to downstream tasks. Although it is…

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

Predictive coding networks are neural models that perform inference through an iterative energy minimization process, whose operations are local in space and time. While effective in shallow architectures, they suffer significant…

Curating a desirable dataset for training has been the core of building highly capable large language models (Touvron et al., 2023; Achiam et al., 2023; Team et al.,2024). Gradient influence scores (Pruthi et al., 2020; Xia et al., 2024)…

We introduce a novel method for partial optimization of the connections in Deep Differentiable Logic Gate Networks (LGNs). Our training method utilizes a probability distribution over a subset of connections per gate input, selecting the…

We study how different output layer parameterizations of a deep neural network affects learning and forgetting in continual learning settings. The following three effects can cause catastrophic forgetting in the output layer: (1) weights…

The theory of greedy low-rank learning (GLRL) aims to explain the impressive generalization capabilities of deep learning. It proves that stochastic gradient-based training implicitly regularizes neural networks towards low-rank solutions…

We consider the supervised learning problem of learning the price of an option or the implied volatility given appropriate input data (model parameters) and corresponding output data (option prices or implied volatilities). The majority of…

Stochastic binary hidden units in a multi-layer perceptron (MLP) network give at least three potential benefits when compared to deterministic MLP networks. (1) They allow to learn one-to-many type of mappings. (2) They can be used in…

All machine learning algorithms use a loss, cost, utility or reward function to encode the learning objective and oversee the learning process. This function that supervises learning is a frequently unrecognized hyperparameter that…

Mixture-of-Experts architectures have become the standard for scaling large language models due to their superior parameter efficiency. To accommodate the growing number of experts in practice, modern inference systems commonly adopt expert…

Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states). However, the…

Goal-conditioned reinforcement learning (GCRL) has a wide range of potential real-world applications, including manipulation and navigation problems in robotics. Especially in such robotics tasks, sample efficiency is of the utmost…