相关论文: When to Ponder: Adaptive Compute Allocation for Co…

Mechanisms for continued self-improvement of language models without external supervision remain an open challenge. We propose Peer-Predictive Self-Training (PST), a label-free fine-tuning framework in which multiple language models improve…

Autoregressive language models like GPT aim to predict next tokens, while autoencoding models such as BERT are trained on tasks such as predicting masked tokens. We train a decoder-only architecture for predicting the second to last token…

Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whether these LLMs can self-improve without the need for…

Semantic routers in LLM inference gateways select tools in the critical request path, where every millisecond of added latency compounds across millions of requests. We propose Outcome-Aware Tool Selection (OATS), which interpolates tool…

We enhance auto-regressive language models by conditioning on document chunks retrieved from a large corpus, based on local similarity with preceding tokens. With a $2$ trillion token database, our Retrieval-Enhanced Transformer (RETRO)…

Often, constraints arise in deployment settings where even lightweight parameter updates e.g. parameter-efficient fine-tuning could induce model shift or tuning instability. We study test-time adaptation of foundation models for few-shot…

Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When faced with challenging shifts, most methods collapse and perform worse than the original pretrained…

The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known as chain-of-thought (CoT). However, CoT often becomes…

Recent test-time reasoning methods improve performance by generating more candidate chains or searching over larger reasoning trees, but they typically lack explicit control over when to expand, what to prune, how to repair, and when to…

Prompt tuning has emerged as a key technique for adapting large pre-trained Decision Transformers (DTs) in offline Reinforcement Learning (RL), particularly in multi-task and few-shot settings. The Prompting Decision Transformer (PDT)…

We propose a novel adaptive approximation approach for test-time resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our…

Currently, pre-trained models can be considered the default choice for a wide range of NLP tasks. Despite their SoTA results, there is practical evidence that these models may require a different number of computing layers for different…

Reinforcement learning with verifiable rewards helps reasoning, but GRPO-style methods stall on hard prompts where all sampled rollouts fail. SORT adds a repair update for those failures without changing rollout generation: it derives a…

Generating high-quality code that solves complex programming tasks is challenging, especially with current decoder-based models that produce highly stochastic outputs. In code generation, even minor errors can easily break the entire…

Generalizing deep learning models to unknown target domain distribution with low latency has motivated research into test-time training/adaptation (TTT/TTA). Existing approaches often focus on improving test-time training performance under…

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the…

Decoding strategies largely determine the quality of Large Language Model (LLM) outputs, yet widely used heuristics such as greedy or fixed temperature/top-p decoding are static and often task-agnostic, leading to suboptimal or inconsistent…

The pre-dominant approach to language modeling to date is based on recurrent neural networks. Their success on this task is often linked to their ability to capture unbounded context. In this paper we develop a finite context approach…

The recent paradigm shift to large-scale foundation models has brought about a new era for deep learning that, while has found great success in practice, has also been plagued by prohibitively expensive costs in terms of high memory…

Large language models (LLMs) exhibit in-context learning abilities which enable the same model to perform several tasks without any task-specific training. In contrast, traditional adaptation approaches, such as fine-tuning, modify the…