跳到正文
研踪PaperTrail

论文库

检索计算机领域论文，按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-15 00:32 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-14 01:09 — 2026-11-15 01:09（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-15 00:32最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 16 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-15 00:30（北京时间）
新论文 · v1arXiv:2611.15054

Reduced-Complexity WMMSE Approach for Cell-Free Massive MIMO Systems With Finite-Capacity Fronthaul Links

Wonsik Yoo, Hoon Lee, Seok-Hwan Park

原文摘要

We propose a reduced-complexity weighted minimum mean squared error (R-WMMSE) framework for cell-free massive MIMO (CF-mMIMO) systems with finite-capacity fronthaul links. To maximize the system capacity, we need to jointly design beamforming vectors at distributed access points (APs) and fronthaul quantization noise covariances. Such a task would be addressed using conventional WMMSE algorithms and their variants. However, existing WMMSE-based methods either assume ideal infinite-capacity fronthaul links or incur high computational complexity when jointly optimizing the network-wide beamforming and fronthaul compression variables. To this end, the proposed method jointly optimizes beamforming and fronthaul compression by leveraging a sequential per-AP optimization strategy. Since each subproblem is efficiently solved via Lagrangian duality with closed-form updates, the overall computational complexity can be significantly reduced compared to the conventional WMMSE method. To further reduce hardware cost, we extend the R-WMMSE framework to hybrid analog-digital beamforming systems, tackling the joint design of digital beamforming, fronthaul compression, and analog beamforming. Numerical results show that the proposed scheme achieves performance nearly identical to that of the conventional WMMSE while reducing the runtime by over 99%.

cs.IT · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15004

A Cardiorespiratory Foundation Model Pretrained on Ten Physiological Signals for Perioperative and Critical Care

Cheol-Hui Lee, Wookyung Kim, Hyeonhoon Lee, Garam Lee, Da-in Eun, Hyung-Chul Lee

原文摘要

Arterial, venous, pulmonary artery and intracranial pressures and ventilator waveforms guide decisions in operating rooms and intensive care units, yet foundation models for physiological waveforms have been built almost entirely on the electrocardiogram and photoplethysmogram. We present CARMEN, a single encoder pretrained without labels on ten cardiorespiratory waveforms (2.27 million modality-hours). CARMEN accepts any combination of co-recorded signals from 10 s to 5 min, and a conditioning mechanism, LSCNorm, restores the absolute signal level that normalization removes; without it, the AUROC for intraoperative hypotension fell from 0.894 to 0.780. Across 19 tasks from Korean and US cohorts, the frozen encoder outperformed supervised models on 12 of 15 and three foundation models, one general-purpose and two for biosignals, on 14 to 17 of 19, with none exceeding it on any task. Given the electrocardiogram or photoplethysmogram alone, it matched or exceeded signal-specific foundation models in most comparisons, and it retained its performance when channels were missing.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12527

WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning

Sang-Hoon Lee, Ha-Yeong Choi

原文摘要

This work proposes WaveGen, a fully end-to-end diffusion-based text-to-waveform framework based on Spectral Forcing, which jointly learns an internal spectral trajectory and the target waveform trajectory within a single model, enabling direct end-to-end text-to-waveform generation. Unlike recent TTS pipelines, WaveGen does not rely on separately trained or externally decoded intermediate representations, such as neural audio codecs, Mel-spectrogram vocoders, or VAE-based latent models. In addition, WaveGen performs internal text-speech alignment within a single model, eliminating the need for external alignment modules such as duration predictors. To preserve a truly end-to-end formulation, our framework further avoids dependence on self-supervised representations, such as BERT-based text embeddings and Wav2Vec 2.0-based semantic representations, as well as semantic distillation methods for training optimization. To achieve this, we carefully design Spectral Forcing, a model architecture with disentangled diffusion heads, and a training objective based on a multi-scale spectral $v$-loss. We further validate the scalability of end-to-end TTS models by scaling the model size from 0.1B to 0.6B parameters. Using a single architecture, open-source data, and one-stage training, without external modules such as duration predictor or REPA, WaveGen demonstrates fully end-to-end waveform generation achieving state-of-the-art performance on the Emilia training dataset. In particular, WaveGen achieves a WER of 1.47 and a SIM of 0.75 on the Seed-en benchmark. Source code and checkpoints are available at https://github.com/sh-lee-prml/WaveGen

cs.SD · cs.AI · eess.AS · eess.SP

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.17403

Pseudometric-Weighted Correlation Clustering via Spectral Preclustering

Chenglin Fan, Dahoon Lee, Euiwoong Lee

原文摘要

We study \emph{pseudometric-weighted correlation clustering}, in which pairs have arbitrary positive or negative labels and nonnegative disagreement weights satisfying the triangle inequality. For every fixed $\varepsilon>0$, we give a randomized polynomial-time $(2+\varepsilon)$-approximation, improving the previous factor of $10/3$. The algorithm constructs an explicit feasible solution to the cluster LP with polynomial support and value at most $(1+\varepsilon)\mathrm{OPT}$, where $\mathrm{OPT}$ is the minimum integral clustering cost. Our main contribution is a weighted preclustering construction that witnesses a near-optimal clustering while bounding the total weight of admissible edges by $\operatorname{poly}(1/\varepsilon)\mathrm{OPT}$. We obtain admissibility certificates from random walks, where the factor-two Ptolemy's inequality for pseudometrics reduces the required length of walks from $O(\log n)$ to a constant. We then bound the rounding error separately at each vertex and use the triangle inequality to control its weighted cost. Sampling and coverage corrections produce an exactly feasible solution, and the factor-two rounding completes the approximation algorithm.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11238

FRESCO: A Novel Consistency Control for Asynchronous Pipeline Parallel Training

Dongyeop Lee, Namhoon Lee

原文摘要

Asynchronous pipeline parallelism can accelerate distributed model training, but suffers from instability caused by inconsistent gradient computations. We identify a fundamental source of this inconsistency: error signals are coupled to forward-time features, not just parameter states. This means that parameters may evolve as long as they preserve forward-equivalence. Leveraging this insight, we introduce FRESCO, which frames asynchronous updates as a constrained optimization problem: it finds the minimal update modification that acts trivially on the activation subspace. We demonstrate that FRESCO consistently outperforms representative asynchronous baselines in LLM pre-training, with the gains most pronounced under deep pipelines and high inconsistency levels: at pipeline depth 32, it reaches the same loss as the strongest baseline with 43% fewer iterations and 30% less wall-clock time, while requiring 8~921$\times$ less memory overhead. Moving beyond the current limitations, FRESCO establishes a new foundation for high-utilization pipeline parallel training, providing a scalable path for large-model development on diverse, resource-constrained systems.

cs.LG · cs.AI · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.02479

Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation

Minseok Joo, Dogyun Park, Taehoon Lee, Kyujin Lee, Hyunwoo J. Kim

原文摘要

Long-horizon video generation is a key capability of video world models, yet maintaining geometric consistency remains challenging. Memory-augmented generative models address this by retrieving historical frames, but their effectiveness depends on two key design choices: what 3D-geometric evidence should represent past observations, and how memory frames should be selected from this evidence. Pose-based field-of-view overlap provides lightweight but coarse geometric evidence, while explicit 3D scene memories offer finer spatial information at the cost of geometry estimation, alignment, and incremental updates over long rollouts. We propose Coverage-Maximizing Retrieval-Augmented Generation (CovRAG), a depth-based memory retrieval framework that uses pretrained 3D priors to construct a target-view coverage map as lightweight 3D memory evidence. For frame selection, CovRAG maximizes residual coverage gain, iteratively retrieving frames that explain target-view regions not covered by the temporal context or previously selected memories. To improve scalability in long-video generation, we introduce sliding-window depth caching for efficient geometry estimation. Experiments on RealEstate10K and DL3DV10K show that CovRAG improves long-horizon geometric consistency over the evaluated memory-retrieval baselines while maintaining low retrieval latency.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.03056

MOF-VERIFY: A Failure-Aware Agentic Harness for MOF Hypothesis Verification

Donghyun Lee, Taehoon Lee, Geonhee Ahn, Jieun Kim, Jihyun Park, Suyeon Cho, Yoona Kim, Chaerim Shin 等 13 位作者

原文摘要

Large language models are increasingly used as reasoning components in AI-driven materials Co-Scientists, yet the reliability of the resulting verification pipeline remains unclear. Metal-organic frameworks (MOFs) provide a particularly challenging setting because structures may appear under different identifiers, synthesis outcomes depend strongly on experimental conditions, evidence is distributed across heterogeneous sources, and some hypotheses require computation rather than literature alone. We introduce a diagnostic benchmark with four task families covering structural grounding, synthesis-condition verification, evidence-sufficiency verification, and MLIP-based computational verification. T-MOF-1-3 are evaluated under closed-book, retrieval-enabled, and oracle-evidence settings to localize failures in knowledge access, evidence acquisition, and reasoning, while T-MOF-4 separately evaluates computational verification. Guided by these diagnosed failure modes, we develop MOF-Verify, a failure-aware agentic harness that targets structural, literature, evidence-sufficiency, and computational bottlenecks before producing a final verdict. Across multiple backbone LLMs, MOF-Verify improves the reported average over direct inference and retrieval-based baselines on this benchmark, with gains concentrated in structural grounding and evidence sufficiency. Benchmark records and release-status documentation are available at https://github.com/IMMS-Ewha/MOF-Verify-Benchmark.

cs.AI · cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06035

TRACK: Multiple Instance Learning for Anti-Money Laundering in Transaction Networks

Seonkyu Lim, Inwoo Tae, Gwangui Hong, Jaehoon Lee, Jeongwhan Choi, Taehoon Kim, Min-Soo Kim, Yongjae Lee

原文摘要

Anti-money laundering (AML) investigations are organized around accounts, while the suspicious evidence for an account may reside in only a few of its transactions. Yet many account-level detectors summarize transactions before learning, and message-passing models may aggregate once more over neighboring accounts. We name this discrepancy the aggregation mismatch and study it under an account-window benchmark label defined by the presence of at least one flagged transaction. We recast account-level AML detection as multiple instance learning, in which an account-window is a bag and its transactions are instances. We propose TRACK, which encodes every transaction with a shared encoder and selectively pools the encodings into an account decision. To emulate coarse supervision, we withhold the transaction labels of five AML datasets from TRACK throughout training. Under a time-ordered protocol, TRACK achieves the highest average precision among the tabular and graph baselines trained from account labels on every dataset. Despite using only account-window supervision, it remains competitive with edge classifiers trained directly from transaction labels. Its instance scores also rank flagged transactions well above chance and approach or exceed directly supervised ranking performance across datasets.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05954

Robots in the City: Persona-Based Perceptions of Urban Robots

Keonhee Jang, Kanghoon Lee, Seokwoo Yun, Namwoo Kim, Yoonjin Yoon

原文摘要

Pedestrians increasingly encounter robots in urban public spaces without interacting with them, but how robots change the perceived safety of a street remains unclear. We examine how robot presence and type affect perceived safety across urban contexts. We generate 18 images of Seoul streets that vary in time of day, road class, and robot condition (no robot, a delivery robot, or a humanoid). Two multimodal large language models (MLLMs), Qwen3.8-27B and Gemma4-26B, each conditioned on 500 synthetic personas, choose the safer image in each pair, and 25 human respondents complete the same task. Both models prefer streets without robots and favor the delivery robot over the humanoid. Robots are chosen more often at night and less often by older personas, whereas road class has smaller effects. In the model rationales, the delivery robot appears as a physical obstacle, whereas the humanoid appears as either a threat or a source of protection. Like humans, both models chose robots more often at night, but chose the humanoid over the delivery robot far less often, and Gemma showed a night effect for the humanoid about three times that of humans. These results show that the effect of a robot on perceived safety depends on when it appears, and that persona-conditioned MLLMs capture only part of human judgments.

cs.HC · cs.CL · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.30435HF 社区推荐

Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models

Taewhoo Lee, Minju Song, Jungwoo Park, Chanwoong Yoon, Junha Jung, Hyeon Hwang, Sanghoon Lee, Minbyul Jeong 等 9 位作者

原文摘要

Recent advances in search agents have enabled large language models to tackle complex tasks by retrieving and synthesizing external information. However, existing search agents often lack search-state awareness, i.e., the ability to recognize what information has been obtained and what remains missing, leading to hallucinated reasoning and prematurely terminated search. To address this limitation, we propose Self-Assessment Reinforcement Learning (SARL), a reinforcement learning framework in which models learn to recognize their own search state during training and improve their search behavior accordingly, without requiring additional assessment at test time. SARL achieves this through a dual reward design that captures the corrective effect of each assessment while penalizing excessive reliance on it, jointly encouraging effective and efficient search trajectories. Under this setup, SARL achieves a 24.3% relative improvement over the strongest baseline, with average gains of 35.9% on multi-hop reasoning and 27.9% on deep research benchmarks against the strongest per-benchmark baselines. SARL further surpasses methods built on auxiliary supervision or multi-agent coordination, despite operating as a standalone RL framework with no inference-time scaffolding. Beyond final performance, SARL maintains training stability under extended search horizons, a regime where existing methods consistently degrade, enabling sustained gains as task complexity grows.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.107ACL Anthology · ACL 2026

Let LLM Tutors Ask First: Proactive LLM-Based Tutoring at Scale in a 1,500-Student Online Classroom

Jonghoon Lee, Geonjae Youn, Seongmin Lee, Chaemoon Im, Joongheon Kim, Chuck Yoo

原文摘要

Large-scale introductory CS courses, often enrolling thousands of students, struggle to provide personalized support and encourage active participation. While recent large language models (LLMs) have enabled AI teaching assistants at scale, most existing systems remain reactive, responding only after students explicitly initiate queries. We present SCALA, a student-centered AI learning assistant designed to provide proactive support for students. SCALA introduces predictive query management, a mechanism that generates likely student questions and answers ahead of lectures. Students may choose to view these pre-generated question–answer pairs or engage in interactive conversations with our tutoring model via the same interface. We evaluate SCALA through a semester-long deployment in an undergraduate Python course with over 1,500 students, and find that predictive queries are frequently selected in practice and substantially overlap with real student questions. Based on student feedback, learners preferred SCALA’s responses to their real queries over alternatives such as GPT-4o. These results suggest proactive support as a promising direction for future development of AI-powered teaching assistants. We will release our codebase and interactive demo upon acceptance.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.653ACL Anthology · ACL 2026

ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization

Suyoung Bae Sung Kyun Kwan University, CheolWon Na Sungkyunkwan University, Jaehoon Lee Sung Kyun Kwan University, Yumin Lee Sung Kyun Kwan University, YunSeok Choi SungKyunKwan University, Jee-Hyong Lee Sungkyunkwan University

原文摘要

As Large Language Models (LLMs) have become capable of generating long and descriptive code summaries, accurate and reliable evaluation of factual consistency has become a critical challenge. However, previous evaluation methods are primarily designed for short summaries of isolated code snippets. Consequently, they struggle to provide fine-grained evaluation of multi-sentence functionalities and fail to accurately assess dependency context commonly found in real-world code summaries.To address this, we propose ReFEree, a reference-free and fine-grained method for evaluating factual consistency in real-world code summaries. We define factual inconsistency criteria specific to code summaries and evaluate them at the segment level using these criteria along with dependency information. These segment-level results are then aggregated into a fine-grained score. We construct a code summarization benchmark with human-annotated factual consistency labels. The evaluation results demonstrate that ReFEree achieves the highest correlation with human judgment among 13 baselines, improving 15-18% over the previous state-of-the-art. Our code and data are available at https://github.com/bsy99615/ReFEree.git.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.95ACL Anthology · ACL 2026

Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence

Jinseok Chung Pohang University of Science and Technology, Minkyoung Song, Hyunji Jung POSTECH, Namhoon Lee Pohang University of Science and Technology

原文摘要

In-Context Learning (ICL) allows large language models to adapt to new tasks from a few demonstrations, but its reliability remains a concern: predictions are highly sensitive to both prompt design and the model’s ability to understand the context, obscuring whether failures arise from data properties or model limitations. Uncertainty decomposition—separating aleatoric from epistemic sources—is particularly crucial in this setting, yet existing methods, designed for standard generation tasks, fail to capture the unique dynamics of ICL. To address this, we introduce a concept of self-function vectors, built upon Bayesian views and the mechanistic interpretability of ICL. These vectors leverage internal model representations to model the latent concept learned during in-context prompting, thereby enabling a direct estimation of aleatoric uncertainty within a Bayesian framework and circumventing the reliance on brittle input or decoding manipulations. Given the lack of established benchmarks and suitable evaluation protocols, we also propose the first and rigorous evaluation framework, initially grounded in synthetic tasks for conceptual development and subsequently extended to real-world datasets, in which aleatoric and epistemic uncertainty can be quantified separately under controlled settings. Moreover, we show it can be used as a practical tool for trustworthy-related applications, such as hallucination detection. Our findings pave a new direction for connecting the quantitative view of uncertainty with the mechanistic understanding of model behavior.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

版本更新 · v2arXiv:2604.14615Google Research

用于从可穿戴传感器数据中优先筛选候选生物标志物的AI联合数据科学家

An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data

Yubin Kim, Salman Rahman, Samuel Schmidgall, Chunjong Park, A. Ali Heydari, Ahmed A. Metwally, Hong Yu, Xin Liu 等 36 位作者

AI 速读 基于摘要

CoDaS是一个在人类监督下整合多智能体假设生成、确定性统计分析、对抗性验证与文献解读的AI联合数据科学家，用于从可穿戴设备数据中优先筛选与心理健康和代谢终点相关的候选生物标志物关联。

cs.AI

arXiv ↗PDF ↗
查看原文摘要

Wearable devices generate continuous physiological and behavioral data, but converting these signals into clinically reviewable biomarker hypotheses remains labor-intensive. We introduce CoDaS, an AI co-data-scientist that integrates multi-agent hypothesis generation, deterministic statistical analysis, adversarial validation and literature-grounded interpretation under human oversight. Across three wearable cohorts comprising 9,279 participant-observations, CoDaS prioritized candidate associations for mental-health and metabolic endpoints after internal checks for replication, stability, robustness and leakage. The system identified related circadian-instability signals associated with depression, including sleep-duration variability in DWB ($ρ$ = 0.252, $p$ < 0.001) and sleep-onset variability in GLOBEM ($ρ$ = 0.126, $p$ < 0.001), and derived a wearable cardiovascular-fitness index associated with insulin resistance (steps/resting heart rate; $ρ$ = -0.374, $p$ < 0.001). Adding these features to demographic models produced modest gains ($ΔR^2$ = 0.040 for depression, 0.021 for insulin resistance). In a 12-clinician review totaling approximately 25 active hours, clinician validity judgments aligned with CoDaS confidence tiers ($ρ$ = 0.67, $p$ = 0.005), whereas added clinical value and confidence to act were rated lower. CoDaS supports traceable, hypothesis-generating prioritization of wearable candidate biomarkers.

版本更新 · v5arXiv:2403.05530Google Research

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent 等 1137 位作者

原文摘要

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2408.03314Google Research

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Charlie Snell, Jaehoon Lee, Kelvin Xu, Aviral Kumar

原文摘要

Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. In this paper, we study the scaling of inference-time computation in LLMs, with a focus on answering the question: if an LLM is allowed to use a fixed but non-trivial amount of inference-time compute, how much can it improve its performance on a challenging prompt? Answering this question has implications not only on the achievable performance of LLMs, but also on the future of LLM pretraining and how one should tradeoff inference-time and pre-training compute. Despite its importance, little research attempted to understand the scaling behaviors of various test-time inference methods. Moreover, current work largely provides negative results for a number of these strategies. In this work, we analyze two primary mechanisms to scale test-time computation: (1) searching against dense, process-based verifier reward models; and (2) updating the model's distribution over a response adaptively, given the prompt at test time. We find that in both cases, the effectiveness of different approaches to scaling test-time compute critically varies depending on the difficulty of the prompt. This observation motivates applying a "compute-optimal" scaling strategy, which acts to most effectively allocate test-time compute adaptively per prompt. Using this compute-optimal strategy, we can improve the efficiency of test-time compute scaling by more than 4x compared to a best-of-N baseline. Additionally, in a FLOPs-matched evaluation, we find that on problems where a smaller base model attains somewhat non-trivial success rates, test-time compute can be used to outperform a 14x larger model.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗