Related papers: Revisiting Auxiliary Losses for Conditional Depth …

Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-hoc. Disconnected from the active execution loop, such assessments identify errors that…

Reinforcement learning (RL) has become a key driver of progress in large language models, but scaling RL to long chain-of-thought (CoT) trajectories is increasingly constrained by backpropagation over every generated token. Even with…

Standard negative log-likelihood (NLL) for Supervised Fine-Tuning (SFT) applies uniform token-level weighting. This rigidity creates a two-fold failure mode: (i) overemphasizing low-probability targets can amplify gradients on noisy…

The Winner Determination Problem (WDP) in combinatorial auctions is NP-hard, and no existing method reliably predicts which instances will defeat fast greedy heuristics. The ML-for-combinatorial-optimization community has focused on…

We show that gating mechanisms in recurrent neural networks (RNNs) induce lag-dependent and direction-dependent effective learning rates, even when training uses a fixed, global step size. This behavior arises from a coupling between…

Fine-tuning pretrained contextual word embedding models to supervised downstream tasks has become commonplace in natural language processing. This process, however, is often brittle: even with the same hyperparameter values, distinct random…

Large Language Models (LLMs) can perform many NLP tasks well, but fully fine-tuning them is expensive and requires a lot of memory. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA reduce this cost by adding small low-rank…

When using deep, multi-layered architectures to build generative models of data, it is difficult to train all layers at once. We propose a layer-wise training procedure admitting a performance guarantee compared to the global optimum. It is…

Prompt tuning is an emerging way of adapting pre-trained language models to downstream tasks. However, the existing studies are mainly to add prompts to the input sequence. This way would not work as expected due to the intermediate…

This paper proposes Edge-FIT (Federated Instruction Tuning on the Edge), a scalable framework for Federated Instruction Tuning (FIT) of Large Language Models (LLMs). Traditional Federated Learning (TFL) methods, like FedAvg, fail when…

We study quality-latency-resource trade-offs in a documentation-grounded retrieval-augmented generation (RAG) system that uses Low-Rank Adaptation (LoRA) of the generator. We build a manually verified benchmark of 5,144 question-answer…

Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration strategy, applying it at shallow decoder layers often causes…

Humans can learn several tasks in succession with minimal mutual interference but perform more poorly when trained on multiple tasks at once. The opposite is true for standard deep neural networks. Here, we propose novel computational…

We consider decentralized machine learning over a network where the training data is distributed across $n$ agents, each of which can compute stochastic model updates on their local data. The agent's common goal is to find a model that…

Works on implicit regularization have studied gradient trajectories during the optimization process to explain why deep networks favor certain kinds of solutions over others. In deep linear networks, it has been shown that gradient descent…

Zero-shot text classification typically relies on prompt engineering, but the inherent prompt brittleness of large language models undermines its reliability. Minor changes in prompt can cause significant discrepancies in model performance.…

In the area of code generation research, the emphasis has transitioned from crafting individual functions to developing class-level method code that integrates contextual information. This shift has brought several benchmarks such as…

Mixture-of-Experts (MoE) architectures enable efficient model scaling, yet expert routing behavior across underrepresented languages remains poorly understood. We analyze routing dynamics in two architecturally distinct MoE models -- a pure…

Learning in multi-agent systems is highly challenging due to several factors including the non-stationarity introduced by agents' interactions and the combinatorial nature of their state and action spaces. In particular, we consider the…

Deep neural networks (DNNs) are increasingly being used in autonomous systems. However, DNNs do not generalize well to domain shift. Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all…