paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

NeurIPS 2026

VidHalluDoctor: Learning Video Differences to Mitigate Hallucinations in Vision-Language Models

Ziyun Dai, Yang Fu, Henghui Ding

Large Vision-Language Models (LVLMs) show strong video understanding, yet hallucinations persist, with outputs that misalign with the video content. This stems from two primary causes. First, consecutive frames are often semantically similar, so the model can miss visual details. Second, LVLMs may rely on language priors and pay less attention to visual evidence. To mitigate video hallucinations, we propose **VidHalluDoctor**, a training framework that enhances fine-grained discrimination and reduces reliance on language bias. VidHalluDoctor builds video difference samples to improve visual detail recognition, counterfactual samples to reduce prior bias, and consistency-aware reinforcement learning with designed rewards that evaluate both reasoning quality and consistency between the reasoning and answer. To better evaluate video hallucinations, we introduce **VidHalluEva**, a comprehensive benchmark comprising 10,000 videos that covers three progressive hallucination types across diverse scenarios and multi-view settings. Extensive experiments demonstrate that VidHalluDoctor significantly reduces hallucinations while maintaining strong video understanding. Code and dataset will be released.

NeurIPS 2026

Vibe-Spike: An Energy-Preserving EEG Foundation Model Through the Landscape of Neural Coherence

Jun Ye, Yuting Li, Tingting Dan, Guorong Wu

Current foundation models of electroencephalography (EEG) sought to characterize the fluctuations in neural signals, yet this objective stands fundamentally at odds with the intrinsic physiological mechanisms governing brain activity. As with their LLM predecessors, these models pack millions of neurons, even those contributing negligibly small weights, yielding a computational footprint incompatible with resource-constrained portable brain-computer interfaces (BCIs). To overcome these challenges, we propose *Vibe-Spike*, an energy-preserving and biologically-realistic EEG foundation model operating in the regime of oscillatory neural synchronization. Drawing on principles from cognitive neuroscience, our foundation model is designed to recover the masked EEG signals through the transient spikes of spatially coupled neurons, from which self-organized cortical synchronization (aka. *brain rhythms*) emerges to reciprocally modulate ongoing neural firings. Under the hood, we introduce a macro-micro learning mechanism that bridges two scales of neural computation: lower layers capture neural oscillations via a spiking neural network (SNN), while upper layers model oscillatory synchronization across large neuronal populations, with cross-scale interactions learned end-to-end. Taken together, our *Vibe-Spike* sheds new light on learning intrinsic representation of functional neural fluctuations. We pre-train the model to reconstruct segmented EEG signals directly from the synchronized spiking representations using a purely self-supervised objective on a diverse corpus of **75** public datasets. To demonstrate its universal representational power, we conduct massive-scale evaluations across ten heterogeneous downstream datasets, including clinical pathology, sleep staging, and cognitive assessment. *Vibe-Spike* not only facilitates deployment on portable edge devices through its lightweight architecture and energy-preserving inference, but also provides profound neuroscience insights. By further capturing pre- and post-synaptic firing, *Vibe-Spike* unlocks a new pathway for characterizing effective connectivity and the oscillatory synchronization that underpins cognition.

NeurIPS 2026

ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing

Xinghao Chen, Xiangbo Gao, Jiongze Yu, Yuheng Wu, Zhengzhong Tu

Video scene text editing aims to replace text appearing on scene surfaces in a video, such as storefront signs, whiteboards, and product labels, while preserving the surrounding content, motion, and camera dynamics. Although scene text editing has been extensively studied for still images, its video counterpart remains underdeveloped. Existing resources do not provide paired edits over real-world videos, current protocols rarely measure whether the edited region reads as the target string over time, and there is no large-scale open-source benchmark for systematic comparison. To close these gaps, we introduce ViTeX-Bench, a comprehensive benchmark suite for high-fidelity and temporally consistent video scene text editing. Specifically, we first built ViTeX-Dataset, containing 387 real-world 720p videos with precise text-region masks and editing instructions; the 230-training split provides the first such resource with paired editing results built through a semi-automatic pipeline, with the rest forming the evaluation set for standardized benchmarking. In ViTeX-Bench, we propose a three-axis evaluation protocol: text correctness, visual quality, and edit locality, which contains a total of 13 metrics that combine character-level OCR signals with motion and preservation metrics. Our benchmarking experiments indicate that all eight leading video editing models, including both public and commercial models, fail in distinct ways: they either flicker or drift over time, or simply fail to produce the requested editing effects. To further validate the efficacy of our proposed dataset, we trained ViTeX-Edit-14B on the paired training split with a motion-aligned glyph-video conditioning stream. We show that, trained on only 230 high-quality paired videos, ViTeX-Edit-14B achieves the strongest CharAcc among video-native editors (0.688, +11.1\% over VideoPainter) and leads three ranked temporal metrics, reducing the previous best by 2.1\% (Flicker$_f$), 6.6\% (Flicker$_c$), and 1.9\% (Warp$_c$), respectively.

NeurIPS 2026

ViT-AdaLA: Adapting Vision Transformers with Linear Attention

Yifan Li, David Seunghyun Yoon, Viet Lai, Franck Dernoncourt, Jason Kuen, Yu Kong, Trung Bui

Vision Transformers (ViTs) based vision foundation models (VFMs) have achieved remarkable performance across diverse vision tasks, but suffer from quadratic complexity that limits scalability to long sequences. Existing linear attention approaches for ViTs are typically trained from scratch, requiring substantial computational resources, while linearization-based methods developed for large language model decoders do not transfer well to ViTs. To address these challenges, we propose ViT-AdaLA, a novel framework for effectively adapting and transferring prior knowledge from VFMs to linear attention ViTs. ViT-AdaLA consists of three stages: attention alignment, feature alignment, and supervised fine-tuning. In the attention alignment stage, we align vanilla linear attention with the original softmax-based attention in each block to approximate the behavior of softmax attention. However, residual approximation errors inevitably accumulate across layers. We mitigate this by fine-tuning the linearized ViT to align its final-layer features with a frozen softmax VFM teacher. Finally, the adapted prior knowledge is transferred to downstream tasks through supervised fine-tuning. Extensive experiments on classification and segmentation tasks demonstrate the effectiveness and generality of ViT-AdaLA over various state-of-the-art linear attention counterpart.

NeurIPS 2026

ViMU: Benchmarking Video Metaphorical Understanding

Qi Li, Xinchao Wang

Any new medium, once it emerges, is used for more than the transmission of overt content alone. The information it carries typically operates on two levels: one is the content directly presented, while the other is the subtext beneath it—the implicit ideas and intentions the creator seeks to convey through the medium. Likewise, since video technologies became widely adopted, video has served not only as a powerful tool for recording and communicating visual information, but also as a vehicle for emotions, attitudes, and social meanings that are often difficult to articulate explicitly. Thus, the true meaning of many videos does not reside solely in what is shown on screen; it is often embedded in context, style of expression, and the viewer’s social experience. Some forms of such video subtext are humorous, while others carry irony, mockery, or criticism. These implicit meanings can also be interpreted very differently across cultural backgrounds and social groups. However, most existing video understanding models still focus primarily on literal visual comprehension, such as recognizing objects, actions, or temporal relations, and lack a systematic ability to understand the metaphorical, ironic, and social meanings embedded in videos. To bridge this gap, we introduce ViMU (Video Metaphorical Understanding), the first benchmark designed to systematically evaluate the subtext understanding capabilities of frontier models in videos. ViMU assesses whether video understanding models can go beyond literal perception to infer implicit meaning, rhetorical devices, social signals, target subjects, and culturally grounded subtext, while grounding their interpretations in multimodal evidence and answering both open-ended and multiple-choice questions. Importantly, all questions are designed to be hint-free, ensuring that no key evidence is disclosed to models before answering. Extensive experiments show that most frontier models, including closed-source ones, achieve below 50\% overall performance. We further conduct fine-grained analyses to uncover distinctive model behaviors. Disclaimer: This paper contains potentially offensive and harmful content.

NeurIPS 2026

ViLo: LiDAR Localization with Vision-Language Priors

Minghang Zhu, Jianshi Wu, Yuxin Guo, Wen Li, Penghui Shang, Sheng Ao, Cheng Wang

LiDAR localization is a fundamental task in robotics and computer vision, aiming to estimate the global pose of point clouds. Although Scene Coordinate Regression (SCR) has demonstrated state-of-the-art performance in this field, standard SCR methods employ a monolithic network for uniform optimization across diverse scenes, which inevitably suffers from capacity interference in highly degraded scenes. Recent research on Vision-Language Models (VLMs) indicates that they can acquire rich scene understanding priors, providing the adaptive learning capabilities currently missing in localization networks. In this paper, we propose ViLo, the first framework to integrate VLM priors into SCR to fundamentally enhance localization robustness. Specifically, we design a temporally consistent key-frame querying mechanism to extract open-vocabulary degeneracy priors. We then construct a dynamic prior-guided Mixture-of-Experts (MoE) model for adaptive feature learning tailored to varying scenes. Finally, to avoid additional computational overhead during inference, ViLo internalizes the VLM's scene understanding into the 3D backbone via cross-modal distillation, enabling a lightweight, LiDAR-only deployment. Extensive experiments on the Oxford RobotCar and NCLT datasets demonstrate that ViLo significantly outperforms existing state-of-the-art methods, reducing positional errors by impressive margins of 20% and and 51%, respectively.

NeurIPS 2026

ViDiC: Video Difference Captioning

Jiangtao Wu, Shihao Li, Zhaozhou Bian, Jialu Chen, Yiwen He, Runzhe Wen, An Ping, JiakaiWang, Yuanxing Zhang, Jiaheng Liu

The rapid advancement of controllable video editing and agent-driven video generation has exposed a critical bottleneck: the inability of existing Multimodal Large Language Models to accurately perceive and articulate fine-grained differences between videos. Whether diagnosing editing fidelity or detecting training data quality issues, explicit comparative perception serves as an essential infrastructure. To address this capability gap, we introduce the ViDiC task and its corresponding ViDiC-1K benchmark. ViDiC-1K comprises 1,000 curated video pairs annotated with 3,720 fine-grained comparative checklist items, rigorously structured across seven dimensions: subject, style, background, camera work, motion, position, and playback techniques. To ensure reliable evaluation and prevent model hallucination, we propose a novel dual-checklist framework that assesses the accuracy of both similarities and differences separately based on an LLM-as-a-Judge protocol. Extensive experiments on 16 representative MLLMs reveal significant limitations in their comparative reasoning and dynamic difference perception. We hope ViDiC-1K serves as a foundational benchmark to advance continuous multi-video captioning and edit awareness in multimodal intelligence.

NeurIPS 2026

ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution

Long Cui, Weiyun Wang, Jie Shao, Zichen Wen, Gen Luo, Zhang, Linfeng Zhang, Wenhai Wang

Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Learning (ViCO), a novel training algorithm that enables the model to represent images of varying semantic complexities using different numbers of vision tokens. The key idea behind our method is to employ multiple MLP connectors, each with a different image compression ratio, to downsample the vision tokens based on the semantic complexity of the image. During training, we minimize the KL divergence between the responses conditioned on different MLP connectors. At inference time, we introduce an image router, termed Visual Resolution Router (ViR), that automatically selects the appropriate compression rate for each image patch. Compared with existing dynamic high-resolution strategies, which adjust the number of visual tokens based on image resolutions, our method dynamically adapts the number of visual tokens according to semantic complexity. Experimental results demonstrate that our method can reduce the number of vision tokens by up to 50% while maintaining the model’s perception, reasoning, and OCR capabilities. We hope this work will contribute to the development of more efficient MLLMs. The code and models will be released to facilitate future research.

NeurIPS 2026

Very Fast Bayesian Additive Regression Trees on GPU

Giacomo Petrillo

Bayesian Additive Regression Trees (BART) is a nonparametric Bayesian regression technique based on an ensemble of decision trees. It is part of the toolbox of many statisticians. The overall statistical quality of the regression is typically higher than other generic alternatives, and it requires less manual tuning, making it a good default choice. However, it is a niche method compared to natural competitors such as XGBoost, due to the longer running time, making sample sizes above 10000–100000 a nuisance. We present a GPU-enabled implementation of BART, faster by up to 100x in a given GPU vs. CPU comparison, making BART fast enough to be a viable alternative to non-Bayesian algorithms on large datasets, and showing that BART parallelizes better than its non-Bayesian counterparts. This implementation is available in the Python package bartz.

NeurIPS 2026

VeruSAGE-Bench: A Benchmark Suite for Rust System Verification

Chenyuan Yang, Natalie Neamtu, Chris Hawblitzel, Jacob R Lorch, Shan Lu

Large language models (LLMs) have shown impressive capability to understand and develop code. However, their capability to rigorously reason about and formally prove the correctness of software systems remains in question. Current benchmarks for formal proof generation focus on isolated tasks, typically algorithmic-style problems utilizing basic data structures. We curate a new benchmark suite for system-level proof generation, VeruSAGE-Bench, which consists of 849 proof tasks extracted from eight open-source Verus-verified Rust systems, covering operating systems, storage systems, memory allocators, and more. These tasks are much more complicated than those in previous benchmarks, containing on average more than 20x the formal specification (in Lines of Code) and requiring a much broader array of verification techniques. We evaluate five LLMs on VeruSAGE-Bench (o4-mini, GPT-5, Sonnet 4, Sonnet 4.5, Opus 4.5), and demonstrate that different models and agentic setups lead to vastly different success rates and costs. We also show that the best models possess impressive capability in writing correctness proofs and hence should inspire new ways of developing trustworthy software. Meanwhile, some difficult tasks in VeruSAGE-Bench stress even the best model, forcing long reasoning time (over an hour on the hardest tasks, 15.3 min per task on average), high token cost ($13.65 per task on average), and proof failures, which we hope will guide future improvement in model and agents.

NeurIPS 2026

VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation

Boyao Han, Chen Shi, Jingjing Qian, Zhuotao Tian, Li Jiang

Vision-Language-Action (VLA) models have emerged as powerful foundations for robotic manipulation, but their reliance on fixed camera configurations during training makes them brittle to changes in camera count or pose during deployment. To overcome these limitations, we propose VersaCamVLA, a camera-configurable framework that decouples camera-set representation from action learning. VersaCamVLA learns a unified scene-token interface that maps an arbitrary, variable set of posed RGB views into fixed-size latent scene tokens. This is achieved via multi-signal target-view prediction and Wrist-Augmented Pose Sampling (WAPS), which leverages natural wrist-camera motion for free pose diversity. At deployment, a lightweight spatial encoder injects these compact scene tokens into a pretrained base VLA as a supplementary visual condition, requiring no explicit 3D sensing or novel-view rendering. Experiments on RoboTwin, LIBERO, and a real-robot platform demonstrate that VersaCamVLA consistently outperforms prior VLA methods and direct multi-view baselines, maintaining robust performance across varying camera counts and unseen camera poses.

NeurIPS 2026

Vermeer: Autoregressive generative modeling of microscopy predicts protein localization

Sandeep Kambhampati, Eric Zimmermann, Emre Hayir, Kevin K Yang, Fei Chen, Alex X Lu

Fluorescent microscopy provides a rich view into how proteins localize within cells, but it remains experimentally infeasible to image human proteins across all of the different factors that can impact localization. We introduce Vermeer, a channel-adaptive autoregressive generative model for in silico generation of microscopy images of protein localization. Vermeer conditions generations on protein sequences and landmark stains showing the morphology of cells, which enables it to generalize to unseen proteins and cell lines. We show that Vermeer, trained on the Human Protein Atlas, can generate images with substantially improved perceptual quality and biological fidelity over previous proposals. Additionally, Vermeer's autoregressive framework enables flexible generation using varying channel subsets and orderings, enabling zero-shot transfer to data collected under different imaging conditions and channel configurations than those used for training. These results position Vermeer to enable scalable modeling of protein localization and is a step towards generative foundation models that can operate over distinct microscopy datasets.

NeurIPS 2026

VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems

Hezhe Qiao, Hanghang Tong, Ee-Peng Lim, Bing Liu, Guansong Pang

Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliability. Automatic failure attribution is therefore critical, but existing approaches—such as direct prediction of agent–error pairs and agent-first failure attribution—rely on local logs of agent and miss global failures that only manifest over full interaction trajectories, such as cross-step inconsistencies and inter-agent coordination errors. Moreover, directly predicting failures induces a large combinatorial search space, hindering fine-grained attribution. To address these challenges, we propose VerifyMAS, a hypothesis verification framework for agent failure attribution. Instead of directly predicting faulty agents and error types, VerifyMAS formulates and verifies failure hypotheses against full trajectories. This verification-based approach decomposes attribution into trajectory-level error validation and fine-grained agent localization, providing an error-first attribution approach that captures global failure patterns while substantially reducing the search space. We further introduce a hypothesis-based data construction strategy grounded in a structured error taxonomy and fine-tune a specialized LLM verifier model for trajectory-level failure verification and agent attribution. Experiments on Aegis-Bench and Who&When show that VerifyMAS consistently improves diverse backbone models, including open-source Qwen and API-based GPT models, outperforming prior methods without sacrificing inference efficiency for long multi-agent trajectories.

NeurIPS 2026

Verifiers in the Loop: Decoding Time Verification for Code Translation

Tianyang Zhou, Somesh Jha, Mihai Christodorescu, Kirill Levchenko, Varun Chandrasekaran

Test-time scaling is an important mechanism for improving large language models, especially on tasks with deterministic verifiers. Code translation is a canonical example: the source program constrains valid outputs, while compilers, type check- ers, and behavioral checks provide exact pass/fail feedback. Existing approaches typically apply these verifiers only after generation, which is inefficient because early errors corrupt the autoregressive context and are rarely corrected later. We introduce Decoding Time Verification (DTV), a framework that integrates deter- ministic program verification directly into the decoding loop. DTV interleaves generation with verifier calls under a state-machine controller that enforces valid prefixes, using structural-boundary checks and structure-aware rollback to prevent error propagation while reducing wasted tokens. We evaluate DTV on C-to-Rust and JavaScript-to-TypeScript translation. Using Qwen3-4B as the primary genera- tor under matched token budgets, DTV improves pass rates from 72.3% to 82.0% on C-to-Rust and from 33.3% to 46.0% on JavaScript-to-TypeScript relative to matched self-refinement baselines, while using fewer tokens per case; the same trend largely transfers to Gemma-4-E4B. In the evaluated cost-matched grid, DTV achieves a more favorable pass-rate-cost tradeoff than post-hoc verification or sampling-based scaling. These results show that verifier-guided decoding is an effective use of inference-time compute for code translation.

NeurIPS 2026

Verifier-Backed Hard Problem Generation for Mathematical Reasoning

Yuhang Lai, Jiazhan Feng, Yee Whye Teh, Ning Miao

Large Language Models (LLMs) demonstrate strong capability in solving scientific and mathematical problems, yet they struggle to produce valid and challenging novel problems, an essential component for advancing LLM training and enabling autonomous scientific research. Existing problem generation approaches either depend on expensive human expert involvement or adopt naive self-play paradigms, which frequently yield invalid problems due to reward hacking. This work introduces VHG, a verifier-enhanced hard problem generation framework built upon three-party self-play. By integrating an independent verifier into the conventional setter-solver duality, our design constrains the setter’s reward to be jointly determined by problem validity (evaluated by the verifier) and difficulty (assessed by the solver). We instantiate two verifier variants: a Hard symbolic verifier and a Soft LLM-based verifier, with evaluations conducted on indefinite integral tasks and general mathematical reasoning tasks. Experimental results show that VHG substantially outperforms all baseline methods by a clear margin. Our codes are anonymously available at https://github.com/VHGMath/VHG_Math.

NeurIPS 2026

Verifier Choice is a Benchmark Design Variable: Auditing Structural Counting Evaluation in Text-to-Image Models

Shurun Li, Michael H Wang, Haibo Zeng, Long Wang

Automatic evaluation is now central to text-to-image benchmarking, but the verifier that converts generated images into scores is often treated as an implementation detail. We argue that this is unsafe: an automatic benchmark score is a property of the image generator, prompt distribution, verifier, verifier-use protocol, and scoring rule, not of the generator alone. We study this issue in structural counting, a controlled setting where human-visible counts can be audited and where both instance-level object counts and parent-bound substructure counts arise naturally. We construct a verifier-centric audit suite over seven counting objects: cell phones, chairs, and traffic lights for object counting, and clover leaflets, dresser drawer fronts, power-strip sockets, and turbine blades for substructure counting. Across 6,240 generated images from Qwen-Image-2512 and FLUX.2-dev, we compare open MLLM verifiers under count-only, reject-aware, zero-shot and few-shot protocols, plus TIFA-like target-query variants and targeted frontier closed-model sanity checks on two hard objects. We also compare MLLMs with a detector baseline. On a balanced 2,280-image evaluation split, Qwen3.5-27B with few-shot reject/count achieves the best image-level agreement among open verifiers ($\kappa=0.754$) with a small aggregate score gap ($+1.54\text{pp}$), but changing the protocol, model size, or generator distribution can shift automatic scores by tens of points. Targeted GPT-5.5 and Claude Opus 4.7 checks do not remove the failure modes: GPT-5.5 still has only 59.92\% clover valid-count fidelity, while Claude Opus 4.7 has lower same-slice agreement ($\kappa=0.432$). We propose reporting a factorized verifier reliability profile---aggregate score gap, image-level agreement, valid-image count fidelity, rejection behavior, output compliance, and directional bias---rather than a single automatic benchmark score.

NeurIPS 2026

Verified-Source Authority Is Not Generic Sycophancy: Cue-Family Decomposition of LLM Compliance

Abhinav Rajeev Kumar, Paras Chopra

Large language models change their answers when a "verified" source contradicts them. We study this verified-source authority bias across five open-weight families and three closed APIs. On a baseline-correct trivia subset, a verified-source cue endorsing a wrong answer flips 43–87% of responses across seven of the eight models, with a graded hierarchy over cue strengths. We then show this is not generic user sycophancy: across both open-weight families and closed APIs, the same wrong answer endorsed by a verified source vs. by a user produces different behavioral compliance, and a fitted "authority" vector is distinct from a generic assistant/instruction-following direction and from a user-sycophancy direction under causal projection-removal. Applying this vector to neutral prompts induces matched wrong-answer flips, and the same trivia-fit vector transfers without refitting to PIQA (a held-out task) and to multi-turn SYCON dialogues. Projecting the vector out at α=1 reduces wrong-source compliance by tens of percentage points on both trivia and PIQA in four of five open-weight families, while capability checks (MMLU-Pro, GSM8K) stay within noise of baseline at our evaluation sizes.

NeurIPS 2026

Verification-Guided Abstraction Generation with Large Language Models for Generalized Planning

Zhenhe Cui, Huaxiang Xia, Hangjun Shen, Kailun Luo, Yong He, LiangWei

Generalized planning (GP), where a single policy solves multiple instances from a common planning domain, remains a challenging problem in AI. Abstraction plays an important role in GP, and Qualitative Numerical Planning (QNP) provides a compact abstract model for GP. However, useful QNP abstractions are difficult to construct and require substantial manual effort and expertise. We study whether QNP abstractions can be generated from PDDL domains and training instances by coupling LLM generation with symbolic reasoning. We propose a generate--debug--repair framework in which an LLM proposes abstract features and constructs a candidate QNP abstraction over the initial states, actions, and goals of the training instances. To improve reliability, we introduce verification-guided repair based on approximate soundness. Given a candidate abstraction, we solve it, validate the induced abstract instances, and apply one of two checking branches: SRCB tests an $m$-simulation relation between induced abstract and concrete instances to target approximate soundness, while PRCB tests whether the induced abstract plan refines into valid concrete solutions. Detected failures are converted into structured feedback for iterative repair. Experiments on seven GP benchmark domains with five LLMs show that verification-guided repair improves LLM-generated QNP abstractions over both single-pass generation and LLM self-repair, and helps some models produce abstractions that transfer across instances. Our results suggest that LLMs can serve as generators of symbolic abstractions for GP when coupled with formal error detection and structured repair feedback.

NeurIPS 2026

Verification-Aware Training for Speculative Decoding

Geonmo Gu, Byeongho Heo, HeeJae Jun, Yoohoon Kang, Sangmin Lee, Sangdoo Yun, Dongyoon Han

Speculative decoding accelerates large language model inference by using a draft model to generate candidate tokens, which are verified by the target model in a single forward pass. Verification proceeds and discards every position from the first rejection onward, yet existing draft training relies on token-level cross-entropy with a fixed per-position weighting that does not reflect this process. We introduce Verification-Aware Training (VAT), a plug-in framework that simulates verification at every training step and turns the resulting accept and reject patterns into supervision. VAT consists of two components: (i) a verification head, a lightweight jointly-trainable binary classifier that validates per-position acceptance via an explicit prediction target; (ii) verification-adaptive weighting replaces the fixed weighting schedule with weights adapted to each sample's first rejection point during training. VAT is model-agnostic and can be layered on top of existing methods without changing the draft architecture, the target model, or the inference procedure, and trained jointly with the original loss. Applied to EAGLE-3 and DFlash on Qwen3-4B, Qwen3-8B and LLaMA3.1-8B, VAT improves average acceptance length by up to 11.4% and wall-clock speedup by up to 8.7%, with consistent gains across math, code, and chat benchmarks.

NeurIPS 2026

Verifiable LLM-Guided Focal SMT Solving for Quantified Arrays

Kunhang Lv, Rui Han, Fuqi Jia, Yuhang Dong, Feifei Ma, Jian Zhang

Large language models can often identify useful semantic structure in formal artifacts, but their outputs cannot be trusted as proofs or solver decisions. We study whether LLMs can instead guide formal reasoning systems through a narrow, solver-verifiable interface. We instantiate this idea in quantified array SMT solving, where modern instantiation-based techniques can fail when key ground terms and equalities are hidden by auxiliary variables, axiom guards, and nested array terms. We observe that many instances are largely driven by a small set of focal ground terms or constraints, similar to the backdoor sets in SAT solving. Building on this, we present LinguaArray, a framework where an LLM proposes a small Semantic Focus Set (ground terms/constraints), while a conventional SMT solver remains the sole proof engine and certifies all results. LinguaArray uses these LLM-suggested, solver-validated finite sets to significantly enhance solver capability, solving additional satisfiable and unsatisfiable instances that the backend alone fails to solve. It interacts within a finite time and then falls back to the backend solver to mitigate potential regressions. Evaluation on 1015 SMT-LIB instances across five logics under 1200s timeout (including LLM latency) shows that LinguaArray solves up to 69.1\% of instances and increases solved-instance counts by 105\%--397\% over the corresponding backends.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →