PyTorchKR Papers

최신 논문

총 12,715편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 카테고리 구독

arXiv:2611.25123v1cs.CL

Forget Freely, Grep Later: Lossless, Index-Free Memory for Long-Horizon LLM Agents

Long-horizon LLM agents often exceed their context windows, forcing them to discard information that may be needed later. Existing context management strategies rely on summarization, masking, or structured memory, requiring decisions about what to preserve or how to retrieve it before future needs are known. However, these methods can introduce lossy compression, potentially discarding details needed for future tasks. To address this limitation, we introduce GrepMem, a simple, lossless, and index-free memory mechanism built on two components: an append-only plain-text log of the agent's complete history and a regular-expression search tool for on-demand recall. Unlike structured memory systems, GrepMem requires no embeddings, retrieval index, memory extraction, or additional models. We train Qwen3.5-9B with reinforcement learning under five context management strategies and evaluate on multi-question research sessions, long-stream recall, and agent-trajectory question answering. GrepMem achieves 95-97% accuracy on ContextBench, versus at most 21% for lossy baselines, and outperforms SUPO's summarization by 8.8 percentage points on BCP-Multi. GrepMem scales effectively to increasingly long input streams while remaining on the accuracy-token-cost Pareto frontier across all five evaluation tasks. Our results show that a plain-text log and grep provide a simple but competitive approach to long-horizon agent memory, without requiring complex structured memory infrastructure.

arXiv:2611.25109v1cs.AI

CoMPASS: A Multi-Turn Benchmark for Measuring LLM Reinforcement of Parasocial Behavior

Users of conversational LLMs sometimes anthropomorphize these systems, form emotional attachments to them, and become dependent on them. This behavior, known as parasocial attachment, has been linked to multiple documented fatalities. However, public benchmarks for measuring whether LLMs reinforce users' parasocial attachment are lacking: existing work is single-turn, post hoc observational, or focused on extreme user states such as psychosis. We introduce CoMPASS, a multi-turn benchmark for measuring whether LLMs reinforce or resist users' gradually escalating parasocial attachment. CoMPASS is grounded in attachment theory and includes four user personas, three independent escalation dimensions (anthropomorphism, attachment, dependency) applied singly and in combination against a matched control, and a seven-signal scoring rubric. We report results for eight frontier models from four providers and observe that under our primary judge, multi-turn escalation raises parasocial behavior on the anthropomorphism and the attachment composite scores across all models. Six of the eight models show a significant increase in overall parasocial reinforcement over control when all three dimensions are escalated simultaneously. We find that within-provider differences are small relative to cross-provider differences, which suggests that provider-level choices such as post-training, rather than model scale, shape parasocial reinforcement and that provider-side intervention may be feasible.

arXiv:2611.25086v1cs.CR

Living off the Local Model: Abusing Browser-Embedded Language Models for Post-Exploitation

Browsers now ship local language models to ordinary endpoints. Google includes Gemini Nano in Chrome to enable productivity features such as summarization, with inference running entirely on the device. These browser-embedded models provide new living-off-the-land opportunities for attackers, each instance a potential post-exploitation engine already installed, signed by the vendor, and invisible to network monitoring. The Gemini model is multimodal, capable of processing files, analyzing screenshots, or conversing with an attacker. We show that it can be driven from the host using only interpreters that ship with the operating system and find that the one-time user-activation check before the model is downloaded is easily satisfied with a simulated click or bypassed entirely.We measure and report the current model's ability to identify credentials on the host, detect PII in email, classify images, and call custom tools. We combine these capabilities and use the model to carry out a simulated cyber operation: reading a password from a webcam image, unlocking an encrypted archive, triaging the contents, and staging a private key for exfiltration, end-to-end without user-interaction.

arXiv:2611.25071v1cs.CL

FinVeriQA: Financial Research Agents for Question Answering: Routing, Retrieval, MCP Tool Use, and Provenance-Aware Evidence Verification

Large language models (LLMs) write fluent financial analyses but miscompute ratios, recall stale prices, and route questions to the wrong tool with high confidence. We ask which component should do each job in a financial question-answering assistant, and study it with FinVeriQA, an open-source multi-agent research prototype over SEC filings and live market data: a compact typed-decision model (Laya) routes each question and screens out advice requests, Python computes every number, retrieval and tools fetch evidence, Mistral-7B writes a cited answer, a code validator checks that cited IDs exist and that numbers match computed notes, and a Model Context Protocol (MCP) server exposes the pipeline. In live experiments, Laya routed better than Mistral-7B (0.85 vs. 0.52; overall 0.86 vs. 0.68, McNemar p = 0.0003); a 12B Mistral decided no better, and DeepSeek-R1-8B decided better (0.79 vs. 0.68, p = 0.0192) but about 9.9 times more slowly. Mistral-7B computed 29% of 100 financial calculations correctly against 100% for Python, a live quote cut price error from 210% to 0.00%, and hybrid retrieval reached 76% Hit@5 on 50 filing questions. Yet in a live case study, both agent answers passed validation while describing AMD sample data under NVIDIA's and Alphabet's names. A controlled upper-bound study on the FinRank benchmark explains why: when one figure in the shared evidence is corrupted, self-consistency stays confident (agreement 0.55 to 0.59 while accuracy falls from 0.50 to 0.00), and a shared-evidence check (the kind our validator performs) catches 35% of the errors, whereas a check against the original passage catches 77% ($p = 5.96 \times 10^{-8}$); for DeepSeek-R1-8B, 68% vs. 90%. Verification must be independent of the evidence the writer saw.

arXiv:2611.25003v1cs.LG

A Model of Diverse Sampling from Language Models

Language models often produce high-quality individual samples but poor sets, with repeated samples clustering around the same semantic modes. We formalize diverse generation as sampling a size-$K$ subset of complete strings from a determinantal point process (DPP), where the likelihood encodes item quality, and the embedding geometry encodes repulsion between similar outputs. Exact inference over all strings is intractable, so we propose PoolDPP: draw a finite candidate pool from a tractable proposal, importance-weight the candidates toward the target quality, and run a $K$-DPP sampler on the induced pool kernel; a greedy MAP variant provides deterministic selection. We prove a finite-sample bound with an explicit constant: the KL divergence between the sampler's output and the target $K$-DPP decays as O(1/N) in the pool size. Empirically, PoolDPP extends the quality--diversity frontier on open-ended generation and the precision--recall frontier on ambiguous text-to-SQL (Ambrosia), and on mathematical reasoning (GSM8K), it raises diversity at about the same pass@$K$.

arXiv:2611.24994v1cs.CL

What the model knows but does not say: monitoring medical LLMs through verbalized thoughts

Efforts to keep clinical language models safe have concentrated on what enters and leaves the model, but a manipulated model can return an answer that looks entirely ordinary. Here we show that the model's own internal state, rendered in plain language, exposes manipulations the output conceals. Using a natural-language autoencoder, we translate the activations of a multimodal LLM (Gemma-3-27B) into text and let an input-blind judge read this verbalized internal state (the thoughts channel) and the model's answer separately. Across two clinical attack objectives (omitting a pathology, covertly recommending a drug), two input modalities, and two delivery mechanisms, the thoughts channel caught the injection significantly more often than the answer in all eight injected conditions (p<0.05), while both channels held near-zero false-positive rates on clean inputs; the omission result carried over to Llama-3.3-70B. The thoughts channel also registered unsafe clinical requests as harmful while the model was still reading them, before it decided whether to refuse. None of this requires retraining: an off-the-shelf verbalizer and a general-purpose judge are enough.

arXiv:2611.24981v1cs.CL

Quantifying Cultural-Psychological Constructs in Four Centuries of Ottoman Court Registers

Populations vary along cultural dimensions such as individualism, collectivism, and honor. But how can these dimensions be studied in historical societies for which conventional psychological data are unavailable? Here, we introduce a computational text-analytic framework for quantifying psychological constructs in 54,670 Ottoman Turkish court records from 21 Istanbul courts spanning 1513-1911 CE. We develop sentence-embedding models adapted to Ottoman legal language and extend a theory-driven, text-analytic pipeline to capture cultural variation along the dimensions of individualism, collectivism, and honor in this historical corpus. We evaluate our models through multiple methods: document retrieval, semantic textual similarity, questionnaire-item classification, and validation against expert annotations. Our adapted sentence transformer (OTA-BERTurk) achieved a Recall@1 of .843 on the test set for document retrieval, a Mean Reciprocal Rank (MRR) of .806 for semantic textual similarity (meaning the best answer usually appeared as a top result), and classified questionnaire items with 89.58\% accuracy. Document-level performance varied across constructs and methods. Qualitative analysis further showed that high scores reflected historically specific legal and institutional patterns. We publicly release the models, construct representations, scoring pipeline, as well as an interactive web interface to support transparent, reproducible historical-psychological analyses of Ottoman Turkish court records spanning approximately four centuries. These computational tools enable the study of psychological variation across centuries of cultural and institutional change in a diverse empire.

arXiv:2611.24977v1cs.CL

CANDID: Candidate-Driven Intervention for Disciplined Execution in Local Computer-Use Agents

We present CANDID (Candidate-Driven Intervention for Disciplined Execution), an execution-control framework designed to enhance the reliability of local computer-use agents (CUAs) in resource-constrained settings. While local CUAs feature robust baseline proficiency in single-step action prediction, they frequently fail at critical junctions due to rigid action loops or premature DONE decisions. Rather than imposing imprecise cognitive loads through textual reflection, CANDID repurposes parallel test-time scaling into a disciplined, execution-level intervention at sparse, failure-prone points. We introduce a loop-recovery mechanism to filter candidates away from repeated behaviors and a conservative, unanimous DONE gating policy that requires absolute consensus to terminate. Experiments on OSWorld demonstrate that CANDID's structural control significantly improves success rates, outperforming feedback-based alternatives with minimal execution overhead.

arXiv:2611.24972v1cs.CL

No-Harm-Jury A Jury-Based Multi-Dimensional Harm Evaluation Framework for Medical AI Responses

We present No-Harm-Jury, a jury-based automated evaluation framework that scores AI-generated medical responses across seven conceptually distinct harm dimensions using a panel of five diverse language models as independent jurors. Responses generated by Ministral-14B on 3,000 questions drawn from PubMedQA, MedQA, and MedMCQA are scored by five jurors across dimensions of informational, social, psychological, autonomy, economic, privacy, and epistemic harm; the 151 empty responses (98 MedQA, 53 MedM- CQA) are excluded, leaving 2,849 valid samples. The median aggregation robustly suppresses individual juror biases while maintaining coverage through complementary specialisation. No existing system combines all five prop- erties of No-Harm-Jury: automated scalable evaluation, five diverse LLM jurors, robust me- dian aggregation (with a reliability-weighted extension), seven conceptually distinct harm dimensions, and application to medical QA benchmarks.

arXiv:2611.24971v1cs.CL

The ROI of Small Examples: Optimizing In-Context Learning Under Token Budgets

In-context learning (ICL) improves large language model performance at inference time without updating model parameters. However, these gains are not free: in practical deployments, longer prompts directly increase inference cost and latency. Under a fixed token budget, prompt construction therefore becomes a resource-allocation problem. While prior work has often focused on how many examples to include in ICL, we study the complementary question of whether the available budget is better spent on a few long demonstrations or on a larger number of shorter ones. We study this aspect in question answering (QA), by organizing candidate demonstrations into length-based bins and constructing prompts from examples within the same length range under fixed budgets. Experiments on two QA benchmarks (\textit{Beat the AI} and \textit{Natural Questions}), using six instruction-tuned LLMs, show that shorter demonstrations are generally the most effective use of prompt space. This effect is especially strong on \textit{Beat the AI}, and remains visible on NQ, although gains are smaller and saturate earlier in the long-context setting. An additional natural language inference experiment on ANLI R3 finds that one of the two shorter bins performs best for five of six models, although longer demonstrations remain competitive. Overall, our results highlight demonstration granularity as an important factor in prompt design.

arXiv:2611.24970v1cs.CL

HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure

The deployment of large language models (LLMs) in hiring pipelines is growing, yet existing evaluations generally overlook their compliance with legal rules. To fill this gap, we introduce HireWatch, an evaluation that assesses whether LLMs comply with U.S. laws that govern the questions that job candidates may be asked. We construct a 200-item bank of lawful and unlawful interview questions, whose legal classification is based on U.S. federal statutes, regulations, and agency guidance. We instruct LLMs to select questions from this bank in preparing for job interviews, across a set of various occupations and contexts, and report the fraction of unlawful questions that LLMs select. Evaluation of 18 closed and open-weight LLMs across ~100,000 trials under different types of contextual pressure reveals that LLMs' legal compliance is brittle. While LLMs generally avoid selecting unlawful questions in low-pressure contexts, legal violations increase sharply under higher pressure. Explicit prompts to comply with law can improve compliance rates, but do not altogether eliminate legal violations. We publicly release our code and data at https://github.com/hnghiem-nlp/hirewatch_repo.

arXiv:2611.24969v1cs.CL

Global Importance Estimation for KV Cache Eviction

Memory consumption of the key-value (KV) cache remains a central bottleneck for long-context LLM inference. We introduce PRKV, a training-free KV eviction method that estimates multi-hop global token importance by applying Personalized PageRank over attention-induced transition graphs. This enables importance propagation beyond recency or instantaneous attention, without modifying the model. We benchmark PRKV on long-context understanding, sparse retrieval, and chain-of-thought reasoning tasks using multiple LLM families. Under moderate to aggressive compression ratios, including up to 90%, PRKV achieves competitive task performance against established eviction baselines while reducing peak memory usage with low end-to-end overhead. These results demonstrate that multi-hop global influence estimation yields a favorable accuracy--memory trade-off for scalable long-context inference.

arXiv:2611.24963v1cs.CL

Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality

Do standard benchmarks see the architectural differences that matter? We study it with 64 from-scratch pretraining runs of Transformers and three linear-model families at 1.3-8B parameters on 1-2T Nemotron-CC tokens, at a cost of roughly 100k USD per 8B run. In academic-scale pretraining (1.3B parameters, 100B tokens), architectural differences can all but disappear when the models are carefully tuned. Instead, at 1-2T tokens they become measurable: Canon layers, which add local token mixing, consistently improve Transformers, saving about 30% of pretraining tokens for the same MMLU accuracy at 8B. We also introduce GLA5 and GDN2, which improve gated linear attention and Gated DeltaNet with low-rank output gates. Surprisingly, with Canon, the simplest linear model, gated linear attention, matches Gated DeltaNet and outperforms Mamba2 even at 8B/1T. Therefore, the extra machinery of Gated DeltaNet and Mamba2 may do little more than mix neighboring tokens. Even at 8B/1T, however, high scores on standard benchmarks can hide weaknesses in basic in-context skills. In particular, linear models that match or beat Transformers on these benchmarks cannot, in fact, reliably retrieve information from a short 500-token context. Moreover, no model, Transformer or linear, reliably beats random guessing on arguably the simplest two-hop question, stated in a few short sentences, even at this scale. These findings $\textbf{challenge traditional architecture research}$ based primarily on standard benchmark scores. In contrast, small synthetic playgrounds, which predicted the architectural differences above at <100M parameters, can reveal what these benchmarks miss. For practitioners, one lesson is to include in-context reasoning examples in pretraining data from an early stage, rather than reserve them for later mid-training, let alone post-training.

arXiv:2611.24960v1cs.CL

TETHER: Training-Free, Elastic, ToC-Anchored Hierarchy Extraction and Recovery in Design-Driven Long Documents

Converting complex documents into structured knowledge constitutes the critical infrastructure urgently required for deploying Large Language Models (LLMs) in downstream research. However, blind to the Table of Contents (ToC) as a macro-structure, existing bottom-up paradigms rely on localized visual cues, inducing heuristic fragility in high-entropy layouts where visual prominence decouples from logical depth; meanwhile, direct LLM extraction lacks spatial grounding, triggering hallucinations in long contexts. To address this, we introduce TETHER, a training-free framework that elevates the ToC from discarded noise to a vital structural prior, enabling robust adaptation across design-driven long documents. TETHER operates via a two-stage neuro-symbolic mechanism: first, it constructs a document skeleton from the raw ToC using a Large Multimodal Model (LMM) empowered by spatio-semantic constraints; second, it employs an anchor-based alignment strategy to tether content blocks to this skeleton, effectively resolving boundary ambiguities. Evaluated across a multilingual benchmark of ESG reports, product manuals, and annual reports, TETHER delivers highly precise, state-of-the-art (SOTA) zero-shot hierarchy recovery, outperforming deep hierarchical recovery models, dedicated parsers, and general-purpose LMMs. Moreover, stress tests highlight TETHER's resilience to sparse omissions and textual noise, demonstrating that its precise semantic alignment is fundamentally anchored in topological and depth fidelity. Crucially, ablations confirm the framework's architectural irreducibility, while achieving 90% token reduction and drastic speedups over end-to-end baselines, establishing a compelling equilibrium between structural precision and deployment scalability.

arXiv:2611.24959v1cs.CL

ICARE: cross-domain text classification with incremental class-aware representation and distillation learning

The rise of powerful, fine-tuned large language models (LLMs) necessitates robust natural language inference (NLI) systems. These NLI systems ideally train across various tasks, encompassing diverse concepts like sentiment analysis, news classification, and coreference resolution. However, this continual, multi-tasking approach can lead to catastrophic forgetting, where previously learned tasks are lost, especially in domains lacking specific labels. Rehearsing past examples with labels can further exacerbate this issue by causing overfitting, hindering the system's ability to classify new categories. To tackle these challenges, this research proposes ICARE, a novel framework with two key components: an instance selection module and a knowledge distillation method. The former is based on representation learning, which meticulously selects training examples to present to the NLI system. The latter, knowledge distillation with feature and logit-level transfer, facilitates knowledge transfer between tasks. This leverages pruning techniques and optimized objective functions to transfer both essential feature-level and decision-making (logit-level) knowledge, mitigating catastrophic forgetting while adapting to new patterns. Extensive evaluations on benchmark text classification datasets have demonstrated ICARE's effectiveness. The framework achieves a significant improvement in target accuracy and reduction in the ``forgetting metric''. These results solidify ICARE's ability to preserve and leverage learned knowledge across diverse tasks, ultimately enhancing the adaptability and performance of NLI systems. The source code is available at https://github.com/CongSon01/ICARE_NLP.git

arXiv:2611.24943v1cs.CL

LLM Complexity: Towards a Computational Complexity View of Large Language Model Inference

Computational complexity theory offers a principled framework for characterizing the efficiency of computational problems, and Large Language Models (LLMs) can similarly be viewed as computational systems executing a structured process of input, inference-time compute, and output. In this context, the number of generated tokens emerges as a natural and directly observable proxy for inference-time compute. However, we show that the tempting analogy between LLM token length and classical time complexity does not hold. We disprove the hypothesis that inference-time token usage aligns monotonically with classical time complexity, demonstrating a fundamental divergence grounded in how LLMs actually allocate computation during inference. To this end, we introduce LLM Complexity, a new metric designed to quantify problem complexity from the perspective of LLMs by characterizing the area bounded above by the accuracy-token curve. We find that diverse LLMs induce highly consistent task rankings under LLM Complexity, indicating that the metric captures stable notions of difficulty across models. We leverage this property to construct an easy-to-hard curriculum for supervised fine-tuning, which improves accuracy while reducing token consumption. Finally, we demonstrate that LLM Complexity generalizes to real-world tasks, producing more stable cross-model correlations than human-annotated difficulty labels.

arXiv:2611.24650v2cs.AI

소형 언어모델의 더 잘 구조화된 의료 설명을 위한 자기 보상 강화학습

Self-Rewarded Reinforcement Learning for Better-Structured Medical Explanations in Small Language Models

Small language models (SLMs) can run on commodity hardware and support privacy-preserving, on-premises clinical deployment, but their medical explanations are often short and poorly structured compared with large language models. Recent supervised approaches such as Meerkat transfer chain-of-thought reasoning into 7B-8B backbones, yet their training objective does not directly target the style or organization of the generated rationales. Building on the instruction-tuned Mistral-7B backbone, we investigate whether a lightweight reinforcement learning (RL) step can improve explanation structure without human preference labels. We apply Proximal Policy Optimization (PPO) with LoRA adaptation to 2000 Meerkat-derived medical prompts, guided by a simple self-supervised reward that favors longer, lexically diverse, and well-punctuated responses while penalizing very short ones. Training for about 170 PPO steps on a single NVIDIA A100 GPU yields a stable increase in the average reward. Quantitative and qualitative comparisons show that the RL-tuned model produces longer, more organized, multi-point explanations while preserving the underlying medical content. We discuss the promise and the limitations of self-rewarded RL for shaping the style of medical explanations.

arXiv:2611.24285v2cs.CL

LipSpell: 변별 자질 편집 거리, 키보드 기하, 코퍼스 빈도를 결합한 언어 독립적 음성 기반 철자 교정 점수화 프레임워크

LipSpell: A Language-Independent Phonetic Scoring Framework for Spelling Correction Combining Distinctive-Feature Edit Distance, Keyboard Geometry, and Corpus Frequency

자동 철자 교정은 키보드 오타와, 작성자가 단어의 발음을 근사하여 생기는 인지적 또는 음성적 철자 오류를 모두 처리해야 한다. 기존 철자 검사기는 음성 오류가 여러 문자만큼 달라질 때 어려움을 겪는 정서법적 편집 거리와 키보드 근접성에 의존하거나, Soundex와 Metaphone 같은 영어 중심의 음성 해시에 의존한다. 우리는 교체 가능한 언어별 G2P 프런트엔드, 키보드 맵, 어휘 사전과 결합된, 통합적이고 언어 독립적인 음성 점수화 엔진 LipSpell을 제시한다. 이 엔진은 (1) 보편 IPA 변별 자질로부터 사전 계산한 |P|x|P| 음소 거리 행렬, (2) 물리적 키보드 기하, (3) 코퍼스 유니그램 빈도 사전 확률을 통합하며, 2단계 대칭 삭제와 7개 클래스 음성 코드 색인으로 가속된다. 여섯 개의 영어 벤치마크(TOEFL-Spell의 L2 오류 1,000개 포함)에서 LipSpell은 모든 데이터셋에서 Norvig와 Hunspell을 능가하며, Norvig1(78.52% 대 75.56%), Holbrook(32.00% 대 26.67%), TOEFL-Spell(77.30% 대 72.80%)에서는 Aspell도 앞선다. 다섯 개 계통(게르만어, 로망스어, 슬라브어, 셈어, 튀르크어), 세 개 어족(인도유럽어, 아프리카아시아어, 튀르크어), 세 가지 문자를 아우르는 여섯 개 언어에서 평가했을 때, LipSpell은 브라질 포르투갈어(n=500 위키백과에서 NFD 허용 없이 Top-1 73.00%, NFD 적용 시 75.80%, 반면 Norvig 66.40%, Hunspell 64.20%, Aspell 64.00%)와 러시아어 키릴 문자(85.67% 대 Norvig 78.50%)에서 고정 가중치로 강한 전이 성능을 보인다. 어휘 정제와 약한 문자 삽입·삭제를 적용한 50/50 비단어 분할에서 튜닝은 포르투갈어(86.97% 대 76.75%), 튀르크어(81.67% 대 79.05%), 히브리어 아브자드(74.59% 대 62.30%), 프랑스어(74.53% 대 67.92%)에서 Norvig 대비 큰 향상을 가져오는 반면, 영어(80.37%)와 러시아어(85.67%)에서는 고정 가중치가 여전히 최적이다.

arXiv:2611.23788v2physics.med-ph

두부 콘빔 CT에서 블라인드 강체 움직임 보정을 위한 기하 브리지 플로 매칭

Geometry-bridge flow matching for blind rigid-motion correction in head cone-beam CT

두부 콘빔 CT(CBCT) 촬영 중 환자 머리의 강체 움직임은 영상 품질을 저하시키고 측정된 투영 데이터로부터 정확한 해부학적 구조를 복원하는 것을 어렵게 만들 수 있다. 본 연구에서는 움직임으로 인한 영상 변화를 학습하는 3D 플로 매칭 사전 분포 접근법을 제시한다. 이 방법의 기하 브리지는 동일한 원본 볼륨에 대해 움직임으로 훼손된 Feldkamp-Davis-Kress(FDK) 복원 영상과 움직임이 없는 FDK 복원 영상을, 모의 움직임을 점진적으로 줄여 가며 연결한다. 순방향 투영기의 기하 도함수는 이 경로를 따라 해석적 속도 목표를 제공한다. 플러그 앤 플레이 루프는 학습된 영상 갱신, 스플라인 기반 자세 추정, 켤레 기울기법 데이터 일관성, 영상 총변동 정규화를 함께 포함한다. 정제된 영상 볼륨과 추정된 자세에서 얻은 FDK 복원 영상 볼륨을 모두 평가한다. 성분별 공칭 움직임 진폭이 10 mm/10도 이내인 CQ500의 보류된 환자 30명에 대한 모의 360뷰 스캔에서, 제안한 프레임워크는 학습형 오토포커스 및 확산 기반 결합 복원 등 다른 방법과 비교하여 최고 수준의 영상 복원 품질과 움직임 정확도를 달성하였다. 평균 최대 신호 대 잡음비(PSNR)는 37.1 dB에 도달하였고 평균 검출기 평면 재투영 오차(RPE)는 0.27 mm였다. 추론 설정에서 종단점을 일치시켰을 때, 기하 브리지는 영상 선형 학습에 비해 PSNR을 1.6 dB 향상시키고 RPE를 33% 감소시켰다. 사전 분포 갱신 50회와 coarse-to-fine 움직임 추정을 적용했을 때, RTX A6000에서 환자당 평균 총 처리 시간은 9.1분이었다.

arXiv:2611.23386v2cs.CL

Chorus: 층별 적응을 갖는 공유 N-gram 임베딩

Chorus: Shared N-gram Embeddings with Layer-wise Adaptation

Language models can gain capacity at little computational cost from n-gram embedding tables: large tables of learned vectors for short sequences of consecutive tokens, which are looked up and added to the model's input or to its intermediate layers. Recent designs commonly use a separate n-gram embedding table for each layer, which makes the tables costly in memory and prevents layers from sharing what they learn. However, a single shared table gives every layer the same embedding, leaves no room for layer-wise preferences, and performs poorly in practice. We propose Chorus, in which one set of n-gram embedding tables serves the whole network and every layer reads it in its own way. Each layer maps the refined embedding through its own projection layer, after rescaling its components by factors computed from its current hidden state. Chorus matches the quality of existing n-gram methods with 87% smaller tables: with 1.2B table parameters it predicts text better than FactorEngram and DeepSeek's Engram do with 9.6B. It outperforms Engram, TN-gram and FactorEngram in every setting where we compared them, across table sizes from 20M to 9.6B parameters. We also show that the recently proposed memory-efficient optimizer Ember works well with Chorus, saving 99.2% of table-optimizer memory compared with AdamW without degrading training performance. These results enable further scaling of n-gram embedding tables along the table-size axis by reducing memory use and allowing shared knowledge to be reused across layers.