A research field records its open problems in surveys, keynotes and community reports. Those are prose, written every few years, and nobody can ask them who works on a problem now or whether it was settled last year. We argue the problems should be data, and we build the system that makes them so: a hand-curated problem layer carried in unchanged, under an evidence layer rebuilt from a bibliographic index, joined by typed, provenance-carrying links in one graph database and queryable from one language. A language model does four jobs -- per-paper extraction, catalog grounding, per-paper status verdict, and idea generation -- each constrained to a candidate set so out-of-set answers are refused rather than stored. We report a study on two curated catalogs, database research (1,053 problems) and AI research (1,000 problems), each with a prior catalog-only graph. The rebuilt graph answers every question the catalog-only graph answered -- 47 of 47 on databases, 34 of 35 on AI -- plus questions the catalog-only graph refused: recent workers, untouched problems, methods tried, and outside papers bearing on a problem (336 problems, 770 works on databases). The capability we most wanted does not survive its own audit. Of 41 solves and refutes verdicts hand-checked against the papers, 9 are correct, 30 partly correct and 2 wrong; no refutes verdict (0 of 34) disproves an open problem, and only 1 of 7 solves closes the central question. We report that failure in full and draw the design conclusion: a status change must be proposed with its evidence and never applied, making the human reviewer part of the architecture. We close with the data-engineering problems this raises: entity resolution across curated and harvested layers, verifying model status claims, freshness under source quotas, and evaluation without ground truth.
Coflows capture the collective communication requirements of data-parallel applications, and scheduling them well is essential to the performance of modern data centers. We study non-splitting coflow scheduling in a heterogeneous parallel network whose $m$ network cores may be Electronic Packet Switches (EPS), not-all-stop Optical Circuit Switches (OCS), or all-stop OCS, where every flow must be transmitted entirely through a single core. Previous approximation algorithms for this setting have guarantees that grow linearly with the number of cores $m$ or with the maximum flow degree $τ$ of a port, and therefore become weak as data centers deploy more cores. The source of this dependence is the rounding step: rounding each flow to the core holding its largest fractional value can inflate the load of a port by a factor of $m$. We replace this step with an iterative relaxation rounding scheme that handles the input-port and output-port capacity constraints simultaneously. For minimizing the makespan, this yields approximation ratios of $\min\{τ, 3\}$, $2\min\{τ, 3\}$, and $4\min\{τ, 3\}$ for pure EPS, pure not-all-stop OCS, and pure all-stop OCS networks, respectively. For minimizing the total weighted coflow completion time, we obtain approximation ratios of $8\min\{τ, 4\}$, $16\min\{τ, 4\}$, and $32\min\{τ, 4\}$ for the same three architectures. In a hybrid network, the guarantee is governed by the weakest architecture present, so the overall ratios are at most $4\min\{τ,3\}\le 12$ and $32\min\{τ,4\}\le 128$, respectively. Unlike all previous guarantees for non-splitting coflow scheduling in heterogeneous parallel networks, these bounds are absolute constants that do not grow with the number of cores $m$ or with the flow degree $τ$. We also show that the integrality gap of the underlying linear program is at least $2$.
Random access codes (RACs) encode a $q$-ary input string into fewer $q$-ary symbols while allowing any requested input symbol to be recovered with probability above the random-guessing value $1/q$. However, it remains unclear what asymptotic guarantees on compression and recovery probability should be required of RACs. We address this question by introducing the notion of asymptotically good RACs and give two polynomial-time constructions. First, an $[n,k,d]_q$ linear code with $d\ge2$, together with an encoder based on its orthogonal-array property, yields an $(n,n-k)_q$-RAC with worst-case decoding success probability \[ p_{\rm wc}=\frac{1}{q}+\left(1-\frac{1}{q}\right)\frac{d-2}{n}. \] These OA-RACs are asymptotically good whenever the underlying linear codes are, and Garcia--Stichtenoth algebraic-geometry codes give a concrete polynomial-time realization. Second, a direct-sum strategy using OA-RACs derived from $q$-ary Hamming codes and the trivial $(1,1)_q$-RAC yields asymptotically good RAC families at every prescribed RAC rate $R_{\rm RAC}=(n-k)/n\in(0,1)$. Numerical results demonstrate favorable finite-length performance of both constructions.
We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic workloads. Super is a 120B-parameter, 12B-active multimodal model, while Lightning is a smaller 30B-parameter, 3B-active text model; both designed for efficient deployment. Both models combine large-scale distillation, long-context training, and native speculative decoding, while Super further incorporates Indic continued pretraining and agentic software-engineering mid-training. We develop a comprehensive post-training pipeline spanning supervised fine-tuning and reinforcement learning (RLVR and RLHF), complemented in Super by specialized teacher training and multi- teacher on-policy distillation (MOPD). This transforms Super from a text-only base model into a multimodal agent capable of reasoning over text, images, video, and interactive tool environments. We further explore test-time scaling through parallel agent execution and self-verification. Across training and deployment, we jointly optimize capability and efficiency. Indic continued pretraining improves Indian-language benchmarks by up to 9.82 percentage points, while agentic mid-training strengthens software-engineering capabilities and robustness across agent harnesses. The post-trained Super model achieves 51.78% on SWE-bench Pro, surpassing Nemotron 3 Ultra despite using approximately 4.6x fewer active parameters. Post-training MTP boosting improves speculative- decoding acceptance length by up to 21.8% under probabilistic draft sampling, while NVFP4 quantization achieves 99.62% median accuracy recovery relative to BF16. Inference optimizations enable up to 4,856 output tokens/s/GPU on GB200 while sustaining at least 50 tokens/s/user.
We define and study burst-covering codes. We provide some general bounds connecting the parameters of a code with its burst-covering radius. We then provide stronger bounds on the burst-covering radius of cyclic codes, by employing linear-feedback shift-register (LFSR) sequences. For the case of BCH codes we prove a bound on pattern frequencies in LFSR sequences, and using this tool, we bound the burst-covering radius of binary primitive BCH codes and Melas codes. We then present an efficient burst-covering algorithm for cyclic codes. Finally, we present a bound on the critical exponent of cyclic codes based on the burst-covering radius.
Bosi Wen, Yilin Niu, Cunxiang Wang, Xiaoying Ling, Ying Zhang, Pei Ke University of Electronic Science and Technology of China, Hongning Wang Tsinghua University, Minlie Huang
Instruction-following is a foundational capability of large language models (LLMs), with its improvement hinging on scalable and accurate feedback from judge models. However, the reliability of current judge models in instruction-following remains underexplored due to several deficiencies of existing meta-evaluation benchmarks, such as their insufficient data coverage and oversimplified pairwise evaluation paradigms that misalign with model optimization scenarios. To this end, we propose IF-RewardBench, a comprehensive meta-evaluation benchmark for instruction-following that covers diverse instruction and constraint types. For each instruction, we construct a preference graph containing all pairwise preferences among multiple responses based on instruction-following quality. This design enables a listwise evaluation paradigm that assesses the capabilities of judge models to rank multiple responses, which is essential in guiding model alignment. Extensive experiments on IF-RewardBench reveal significant deficiencies in current judge models and demonstrate that our benchmark achieves a stronger positive correlation with downstream task performance compared to existing benchmarks. Our codes and data are available at https://github.com/thu-coai/IF-RewardBench.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Bosi Wen, Yilin Niu, Cunxiang Wang, Pei Ke University of Electronic Science and Technology of China, Xiaoying Ling, Ying Zhang, Aohan Zeng Tsinghua University, Tsinghua University, Hongning Wang Tsinghua University 等 9 位作者
Instruction-following is a fundamental ability of Large Language Models (LLMs), requiring their generated outputs to follow multiple constraints imposed in input instructions. Numerous studies have attempted to enhance this ability through preference optimization or reinforcement learning based on reward signals from LLM-as-a-Judge. However, existing evaluation models for instruction-following still possess many deficiencies, such as substantial costs and unreliable assessments. To this end, we propose IF-CRITIC, an LLM critic for fine-grained, efficient, and reliable instruction-following evaluation. We first develop a checklist generator to decompose instructions and generate constraint checklists. With the assistance of the checklists, we collect high-quality critique training data through a multi-stage critique filtering mechanism and employ a constraint-level preference optimization method to train IF-CRITIC. Extensive experiments show that the evaluation performance of IF-CRITIC can beat strong LLM-as-a-Judge baselines, including o4-mini and Gemini-3-Pro. With the reward signals provided by IF-CRITIC, LLMs can achieve substantial performance gains in instruction-following optimization under lowercomputational overhead compared to strong LLM critic baselines. Our code and model are available at https://github.com/thu-coai/IF-CRITIC.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yinan Liu Northeastern University, Dongying Lin, Sigang Luo, Xiaochun Yang, Bin Wang
Knowledge Bases (KBs) play a key role in various applications. As two representative KB-related tasks, knowledge base completion (KBC) and knowledge base question answering (KBQA) are closely related and inherently complementary with each other. Thus, it will be beneficial to solve the task of joint KBC and KBQA to make them reinforce each other. However, existing studies usually rely on the small language model (SLM) to enhance them jointly, and the large language model (LLM)’s strong reasoning ability is ignored. In this paper, by combining the strengths of the LLM with the SLM, we propose a novel framework JCQL, which can make these two tasks enhance each other in an iterative manner. To make KBC enhance KBQA, we augment the LLM agent-based KBQA model’s reasoning paths by incorporating an SLM-trained KBC model as an action of the agent, alleviating the LLM’s hallucination and high computational costs issue in KBQA. To make KBQA enhance KBC, we incrementally fine-tune the KBC model by leveraging KBQA’s reasoning paths as its supplementary training data, improving the ability of the SLM in KBC. Extensive experiments over two public benchmark data sets demonstrate that JCQL surpasses all baselines for both KBC and KBQA tasks.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Ruoxi Ning, Yongpeng Zhu, Qingcheng Zeng, Tatsuki Kuribayashi Mohamed bin Zayed University of Artificial Intelligence, Freda Shi Vector Institute and University of Waterloo
Training language models and examining their linguistic behaviors have been a common protocol in computational linguistics for studying linguistic phenomena and modeling human language processing. However, work in this area is often limited to proof-of-concept demonstrations with arbitrary model configurations, without considering hyperparameter sensitivity, an important source of variation in model performance. In this work, we replicate three prior studies (Chang and Bergen, 2022; Hu et al., 2020b; Kuribayashi et al., 2024) with hyperparameters varied within a practical range, and show that modest hyperparameter changes can alter some qualitative conclusions about models’ linguistic abilities and even reverse the ranking of model performance. Our results highlight the risk that prior work may have reflected optimization artifacts rather than the genuine inductive biases of model classes, and that hyperparameter sensitivity should receive more attention as a factor that can meaningfully influence model behavior. We suggest future work to report the variation of performance across the configuration space to enhance the reliability and generalizability of conclusions. Code: https://github.com/compling-wat/tune-linguistic-lms.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Junpeng Ding, Zichen Tang Beijing University of Posts and Telecommunications, Haihong E Beijing University of Post and Telecommunication, Mengyuan Ji, Yang Liu, Haolin Tian, Haiyang Sun, Pengqi Sun 等 20 位作者
We introduce SPUR, a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images. SPUR features three key innovations: (1) Panel-Level Fine-Grained Perception: evaluating the visual perception of multimodal large language models (MLLMs) across three dimensions (numerical, morphological, and information localization) on six fine-grained panel types; (2) Cross-Panel Relation Understanding: utilizing complex images with an average of 14.3 panels per sample to evaluate MLLMs’ ability to decipher intricate cross-panel relations; (3) Expert-Level Reasoning: assessment of qualitative and quantitative reasoning across five experimental paradigms to determine if models can infer conclusions from evidence as human experts do. Comprehensive evaluation of 20 MLLMs and four multimodal Chain-of-Thought (MCoT) methods reveals that current models fall significantly short of the expert-level requirements for scientific image interpretation, underscoring a critical bottleneck in AI for Science (AI4S) research.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Pengyue Jia City University of Hong Kong, Yingyi Zhang, Xiangyu Zhao City University of Hong Kong, Sharon Li
Geographic reasoning is a fundamental cognitive capability that requires models to infer plausible locations by synthesizing visual evidence with spatial world knowledge. Despite recent advances in large vision-language models (LVLMs), existing evaluation paradigms remain largely outcome-centric, relying on static datasets and predefined labels that are conceptually misaligned with open-world geographic inference. Such outcome-centric evaluations often focus exclusively on label matching, leaving the underlying linguistic reasoning chains as unexamined black boxes. In this work, we introduce GeoArena, a dynamic, human-preference-based evaluation framework for benchmarking open-world geographic reasoning. GeoArena reframes evaluation as a pairwise reasoning alignment task on in-the-wild images, where human judges compare model-generated explanations based on reasoning quality, evidence synthesis, and plausibility. We deploy GeoArena as a public platform and benchmark 17 frontier LVLMs using thousands of human judgments, which complements existing benchmarks and supports the development of geographically grounded, human-aligned AI systems. We further provide detailed analyses of model behavior, including reliability of human preferences and factors influencing judgments of geographic reasoning quality. We open-source GeoArena to foster future research.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表