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

TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs

Zihan Lin, Xiaohan Wang, Jie Cao, Jiajun Chai, Wei Lin, Guojun Yin, Ran He

Efficient exploration often remains a central bottleneck in reinforcement learning with verifiable rewards (RLVR). Although temperature control and test-time scaling strategies can increase rollout diversity of large language models (LLMs), they either expand the sample budget at rollout time or leave the benefit of exploration unquantified. To this end, we propose Temperature-Grouped Reinforcement Learning (TGRL), which turns temperature-induced diversity into an explicit training signal. For each prompt, TGRL partitions its rollout group into low- and high-temperature subsets, estimates exploration gain through their reward contrast, and allocates this group-level signal as token-level credit using Jensen--Shannon (JS) divergence between the corresponding temperature-scaled next-token distributions induced by the same logits. Notably, TGRL reaches equivalent accuracy up to 36% faster than strong RLVR baselines without expanding the rollout budget. Across 11 benchmarks from diverse domains, TGRL broadly improves over strong RLVR baselines: it improves the six-benchmark math average by 1.6% at 32B, raises CodeForces rating by 196.7 points and LiveCodeBench Pass@16 by 4.4%, and improves ALFWorld/WebShop success rates by 6.3%/4.9%. Comprehensive ablations and wall-clock analysis confirm the efficacy of all proposed components. Code is available at https://anonymous.4open.science/r/TGRL-4877/.

NeurIPS 2026

TGPO: Trace-Guided Policy Optimization for Robot Task Planning via Verifiable Subgoal Generation

Zhihong Liu, Yang Li, RenMing Huang, Chendong Zeng, Cewu Lu, Panpan Cai

Robot task planning in real-world environments requires mapping abstract natural language instructions to executable action sequences under long horizons and complex constraints. While large language models (LLMs) provide strong commonsense reasoning, they often fail to generate reliable and feasible plans. In contrast, symbolic planners ensure feasibility and optimality but require well-specified goals and cannot directly interpret high-level human intent. We formulate robot task planning as learning to generate verifiable subgoals in the Planning Domain Definition Language (PDDL), bridging language understanding and symbolic planning. To address the challenges of sparse and noisy supervision, we propose Trace-Guided Policy Optimization (TGPO), a reinforcement learning framework that improves structured subgoal generation through (i) verifier-grounded rewards, (ii) external correction of intermediate reasoning traces, and (iii) constrained policy updates that incorporate corrected traces into training. We evaluate TGPO on large-scale household planning tasks with long horizons, abstract instructions, and complex constraints. TGPO significantly outperforms prompting-based and reinforcement learning baselines, with the largest gains on abstract tasks. Furthermore, TGPO integrates naturally with symbolic planners and language-conditioned executors, enabling robust long-horizon planning and combinatorial generalization in realistic environments.

NeurIPS 2026

TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks

Yue Meng, Fei Chen, Chuchu Fan

Learning control policies for complex, long-horizon tasks is a central challenge in autonomous systems. Signal Temporal Logic (STL) offers an expressive language for specifying such tasks, but its non-Markovian nature and inherent sparse reward make it hard for standard Reinforcement Learning (RL) to solve. Prior RL approaches focus only on limited STL fragments or use robustness scores as sparse rewards. Our new method TGPO (Temporal Grounded Policy Optimization) decomposes STL into timed subgoals and invariant constraints and tackles the problem in a hierarchical fashion. Its high-level module proposes time allocations for subgoals, and the low-level time-conditioned policy learns to achieve the sequenced subgoals using a dense, stage-wise reward. In inference, we use the critic to efficiently sample time allocations and select the most promising assignment for the policy to rollout. We evaluate in five environments, from low-dimensional navigation to manipulation, drone, and quadrupedal locomotion, and TGPO significantly outperforms baselines (especially for high-dimensional and long-horizon cases), with 31.6% higher success rate compared to the best method.

NeurIPS 2026

TF-PRVR: Training-Free Partially Relevant Video Retrieval for Real-World Generalization

Giyeol Kim, Chanho Eom

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos containing moments relevant to a given text query. Despite recent progress, existing PRVR methods suffer from two key limitations: a fixed video decomposition scheme that causes semantic dilution, and weak cross-domain robustness due to task-specific training. In this paper, we propose TF-PRVR, the first training-free framework for PRVR designed to improve real-world generalization. TF-PRVR leverages frozen vision-language features to construct video-specific hierarchical representations. It derives temporal semantic signals from frame-level features and applies frequency-based multi-scale analysis to identify adaptive temporal boundaries, producing hierarchical segments with coherent event-level semantics. Built on these segments, TF-PRVR constructs a unified multi-scale graph and propagates query relevance across temporally and semantically related nodes. A moment-aware scoring strategy then aggregates temporally aligned relevance across scales, emphasizing consistently supported moments while suppressing isolated false responses. Without task-specific training, TF-PRVR preserves the general-purpose alignment capability of pre-trained vision-language models and avoids dataset-specific overfitting. Extensive experiments on standard PRVR benchmarks demonstrate competitive retrieval performance and strong robustness under cross-domain evaluation, suggesting a practical direction for real-world PRVR.

NeurIPS 2026

TESLA: Native 4D Gaussian Splatting Generation with Temporally Structured Latents

Weiqi Zhang, Junsheng Zhou, Juntong Fang, Kanle Shi, Shenkun Xu, Yu Shen Liu

Diffusion models have achieved remarkable success in image, video, and 3D content creation. However, extending these successes to native 4D model generation remains challenging due to the intricate coupling between temporal geometry and appearance dynamics. Existing approaches typically generate 4D content by synthesizing videos from novel viewpoints, yet they often suffer from poor spatio-temporal consistency across views and time. To address these limitations, we introduce TESLA, a novel feedforward approach for generating native 4D Gaussian Splatting (4DGS) representations. Our key insight is to decouple temporal geometry and appearance generation through a temporally structured latent representation. This decomposition allows us to first establish coarse temporal geometry that captures fundamental structural dynamics, and then synthesize fine-grained appearance details conditioned on this geometric scaffold. To bridge this decoupled representation to the final output, we design a native 4DGS decoder that directly transforms our temporal features into native 4DGS representations, enabling flexible temporal rendering across arbitrary viewpoints and timesteps. Trained on a large collection of curated animated sequences, we extensively evaluate TESLA on the 4DGS generation task, showing superior performance over existing baselines.

NeurIPS 2026

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning

Alliot Nagle, Jakhongir Saydaliev, Dhia Garbaya, Michael Gastpar, Ashok Vardhan Makkuva, Hyeji Kim

Large Reasoning Models (LRMs) achieve impressive performance on complex reasoning tasks via Chain-of-Thought (CoT) reasoning, which enables them to generate intermediate thinking tokens before arriving at the final answer. However, LRMs often suffer from significant overthinking, spending excessive compute time even after the answer is generated early on. Prior work has identified the existence of an optimal reasoning length such that truncating reasoning at this point significantly shortens CoT outputs with virtually no change in performance. However, determining optimal CoT lengths for practical datasets is highly non-trivial as they are fully task and model-dependent. In this paper, we precisely address this and design Terminator, an early-exit strategy for LRMs at inference to mitigate overthinking. The central idea underpinning Terminator is that the first arrival of an LRM's final answer is often predictable, and we leverage these first answer positions to create a novel dataset of optimal reasoning lengths to train Terminator. Powered by this approach, Terminator achieves significant reductions in CoT lengths of 14%–55% on average across four challenging practical datasets: MATH-500, AIME 2025, HumanEval, and GPQA, while outperforming current state-of-the-art methods and reducing inference latency by more than 2$\times$ compared to the original LRM.

NeurIPS 2026

TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection

Dongchan Cho, Juwon Hwang, Keumyeong Kang, Jiho Han, Namsoon Jung

In unsupervised multivariate time series anomaly detection (MTSAD), local variation can inflate reconstruction and forecasting errors, making observation-space discrepancy an unreliable indicator of abnormal system behavior. Since latent-space scoring can mitigate this limitation, we reframe one-class MTSAD as current-point system-state compatibility estimation and propose **TENET**, the **T**ime-point **E**ncoding **Net**work for Multivariate Time Series Anomaly Detection. We define the current-point system state as a latent representation of the target time point, constructed from variable-level temporal context in the input window. TENET constructs this state through a temporal layer that retrieves window context relative to the current point, encodes time with current-point-centered embeddings, and adaptively mixes the retrieved context with the current representation. With this design, TENET treats the input window not as the object to reconstruct, forecast, summarize, or score, but as context for constructing a latent representation evaluated with a fixed standard-normal negative log-likelihood score. Across benchmark datasets, TENET achieves state-of-the-art performance. Additional experiments further show that TENET remains effective under alternative one-class objectives and outperforms substitutions based on generic sequence encoders, suggesting that its advantage comes from decision-aligned representation construction rather than from a specialized scoring rule. These results indicate that one-class MTSAD can be strong when the latent representation is designed around the current time point.

NeurIPS 2026

TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting

Zeyu Zhang, Bradly Stadie

Backtesting large language models on historical events requires reasoning exclusively from information available before a specified cutoff date. Yet models routinely leak post-cutoff knowledge from pre-training into their reasoning, inflating apparent accuracy and undermining evaluation validity. Prompt-based constraints fail when suppressed content is causally related to the prediction, and knowledge unlearning cannot address this problem because temporal compliance is instance-specific: the same fact may be legitimate evidence for one cutoff date and a violation for another. Rather than erasing knowledge, the model must learn **temporal discipline**: selecting evidence conditioned on each instance's cutoff date. We propose **TEMPO** (**T**emporal **E**nforcement via **M**ode-separated **P**olicy **O**ptimization), which trains this discipline via two contributions: (1) a two-mode reward where a leakage mode drives post-cutoff claims to zero as a hard prerequisite before a performance mode optimizes task performance; and (2) a GRPO-based training pipeline that enables the model to discover temporally valid reasoning strategies. We prove that training monotonically decreases leakage, converges to the leak-free optimum, and improves task performance once compliance is achieved. On three prediction tasks and two models, TEMPO reduces leakage from 2$\sim$13\% to 0.6$\sim$3.7\% across all conditions, with task performance improving 6$\sim$13\% where strong pre-cutoff signals exist and maintained where the prediction task is inherently difficult from valid information alone.

NeurIPS 2026

TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios

Zehan Li, Hongjie Chen, Qing Wang, Yuxin Zhang, Jing Zhou, Hang Lv, Mengjie Du, Yaodong Song, Jie Lian, Jian Kang, Jie Li, Yongxiang Li

Spoken Language Models (SLMs) are expected to support natural spoken interaction beyond task completion. However, existing SLM benchmarks primarily evaluate semantic correctness in structured settings and provide limited assessment of interactional behavior grounded in acoustic context. To address this gap, we introduce TELEVAL, a large-scale SLM benchmark for Chinese spoken interaction in instruction-free, audio-conditioned settings. TELEVAL evaluates two complementary aspects: (1) Reliable Content Fulfillment, which measures semantic accuracy of SLMs under diverse acoustic and linguistic conditions, and (2) Interactional Appropriateness, which assesses whether models produce natural and appropriate responses by implicitly grounding behavior in auditory cues. Experiments show that while models perform competitively on semantic tasks, their performance degrades under acoustic variability and in interactional settings. We observe consistent degradation from perceptual instability to interactional errors, and further identify a recurring failure pattern, termed the "Caption Trap", where models tend to describe perceived audio signals rather than produce appropriate interactive responses. These results indicate that current SLMs remain insufficiently aligned with the requirements of natural spoken interaction. TELEVAL provides a targeted framework for evaluating and analyzing interactional behavior in SLMs.

NeurIPS 2026

TED: Text-Axis Evidence Decomposition for Prompted Anomaly Localization

Jinyoung Kim, Geonho Kim, GiJeong Park, Geonu Lee, YoungJoon Yoo

CLIP is a powerful vision-language model, but it was not designed for fine-grained defect localization; CLIP-based anomaly detectors therefore adapt it with prompts or lightweight modules to increase defect sensitivity. We show that stronger sensitivity does not necessarily make local evidence reliable: under domain shift, adapted CLIP-AD models often assign high anomaly scores to both true defects and visually complex normal regions. The issue is not simply missing defect information, but a local scoring rule that decodes defect and hard-normal evidence, having the same anomaly evidence. We propose \textsc{TED} (Text-Axis Evidence Decomposition), a post-hoc scoring method that asks whether each ambiguous response is better supported by source defect patches or by source normal patches mistaken as anomalous. \textsc{TED} compares these supports under the host's normal-versus-anomaly text response, leaves the backbone and prompts unchanged, and requires no target-domain training. It works as a train-free score for raw VLM backbones or as a source-calibrated residual correction for adapted CLIP-AD hosts. Across frozen VLM backbones, \textsc{TED} substantially improves pixel-level localization over raw prompt similarity; across adapted hosts, it improves most pixel-level settings over P-AUROC, P-PRO, and P-AP. Gains are largest under stronger hard-FP competition, with mean localization gain increasing from $+5.0$ in low-competition regimes to about $+10.9$ in mid/high-competition regimes. These results suggest that recoverable defect evidence can already exist in pretrained multimodal representations, but reliable localization requires decoding it against hard-normal competitors.

NeurIPS 2026

TARP: Trace-Anchored Regularization Prior for Retaining Stepwise Reasoning

Wei Li, Tao Feng, Hangjie Yuan, Aojun Lu, Yanan SUN

Reinforcement learning (RL) is increasingly used in post-training to adapt large models to new reasoning tasks. Recent forgetting analyses, however, are mostly answer-centric: they report reward or accuracy on previously learned tasks and implicitly treat stable answers as evidence of stable reasoning. We show that this view is incomplete. In our sequential reasoning settings, externalized reasoning traces can change substantially in structure, strategy, and sample-wise behavior before answer-level metrics visibly collapse, and harder full-parameter staged runs can later degrade into catastrophic forgetting on earlier tasks. We refer to the trace-first regime as \emph{reasoning drift}. To address it, we propose \emph{Trace-Anchored Regularization Prior} (TARP), a trace-centric regularizer that mines reliable reasoning spans from successful rollouts and uses them to build a compact trace-derived quadratic prior for subsequent RL updates. Across multiple reasoning task sequences and model backbones, TARP reduces selected measured drift signals and improves earlier-task preservation in several evaluated settings, while also revealing a retention-verbosity trade-off that answer-only evaluation hides.

NeurIPS 2026

TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability

Krish Sharma, Omar Naim, Soumadeep Saha, Vinija Jain, Aman Chadha, Nicholas Asher

Recent work has promoted task-aware layer pruning as a way to improve model performance on particular tasks, as shown by TALE. In this paper, we investigate when such improvements occur and why. We show first that, across controlled polynomial regression tasks and large language models, such pruning yields no benefit on in-distribution (ID) data but consistently improves out-of-distribution (OOD) accuracy. We further show empirically that OOD inputs induce layerwise norm and pairwise-distance profiles that deviate from the corresponding ID profiles. This leads to a geometric explanation of task-aware pruning: each task induces a task-adapted geometry, characterized empirically by the representation profiles observed on ID inputs. OOD inputs can introduce a distorted version of the task-adapted geometry. Task-aware pruning identifies layers that create or amplify this distortion; by removing them, it shifts OOD representational norms and pairwise distances toward those observed on the adapted distribution. This realigns OOD inputs with the model’s task-adapted geometry and improves performance. We provide causal evidence through controlled distribution shifts and residual-scaling interventions, and demonstrate consistent behavior across model scales.

NeurIPS 2026

TANGO: RNA Topology and Geometry Co-Design

Tianmeng Hu, Biao Luo, Ke Li

Designing RNA sequences that satisfy target tertiary-structure objectives is an important problem in RNA engineering, with broad applications in synthetic biology and therapeutics. Existing $\mathrm{3D}$ RNA design methods have made substantial progress, but they largely treat the target fold as a geometry-only objective. This is incomplete for RNA, whose functional folds are specified not only by tertiary geometry but also by secondary base-pairing topology. We therefore formulate RNA inverse design as a topology-and-geometry co-design problem and propose $\texttt{TANGO}$, a cooperative multi-agent reinforcement learning framework for this task. $\texttt{TANGO}$ adopts a staged curriculum: it first learns a topology-aware policy from secondary-structure targets, then transfers this policy to tertiary-structure targets to train a general co-design model, and finally applies frontier-guided fine-tuning to refine target-specific trade-offs among secondary-structure fidelity, tertiary-structure fidelity, and sequence diversity. Experiments show that $\texttt{TANGO}$ generates diverse and novel designs, improving tertiary- and secondary-structure performance by $18.3\\%$ and $52.7\\%$, respectively, over the strongest baseline.

NeurIPS 2026

TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering

Yuan Sui, Yulin Chen, Yibo Li, Xue Jiang, Yufei He, Yihong Dong, Xiaoxin He, Tianyu Gao, Bryan Hooi

When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure modes *overthinking* and *overacting*, i.e., where the agent repeatedly reasons over information it already has, and where it issues tool calls without integrating recent observations or acquiring new evidence. In this paper, we introduce **TACT** (**T**hink-**A**ct **C**alibration via activation s**T**eering), to detect and mitigate agent drift in the residual stream before it surfaces as a behavioral failure. In specific, we label trajectory steps as overthinking, overacting, or calibrated, and find that their hidden states can separate linearly along two *drift axes*, pointing from calibrated behavior toward each failure mode (AUC $\approx$ 0.9). To mitigate agent drift, we project each step's activation onto these axes at test time and pull drifted ones back toward the calibrated region. Experiments show that TACT outperforms unsteered baselines across SWE-bench Verified, Terminal-Bench 2.0, and CLAW-Eval, lifting average resolve rate by $+5.8$ pp on Qwen3.5-27B and $+4.8$ pp on Gemma-4-26B-A4B-it while cutting steps-to-resolve by up to $26\%$. These gains frame agent drift as a steerable direction in the residual stream, and position TACT as a viable handle for reliable long-horizon agents.

NeurIPS 2026

TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition

Minghao Zhu, Xiao Lin, Mengxian Hu, Xun Zhou, Liuyi Wang, Xiaoyan Qi, Chengju Liu, Qijun Chen

Adapting CLIP for open-vocabulary video recognition necessitates a delicate balance between newly acquired video knowledge and the pretrained generalization. While existing studies pursue this generalization-specialization trade-off with additional regularizations or constraints, we argue that they overlook the deviation of representations beyond the fine-tuning data distribution, resulting in suboptimal adaptation effects. We believe such deviation is inherited from the inconsistency between the fine-tuning and evaluation objectives, where model optimization is restricted to the known training distribution but evaluated on unseen ones. In this paper, we introduce \emph{TACO}, a simple yet effective framework to mitigate the potential negative effects induced by this inconsistency. Our key insight is that adaptation should preserve OOD-relevant alignment beyond the training distribution. To this end, we propose \emph{Relative Structure Distillation}, which regularizes the relative geometry of the representation space and suppresses harmful alignment shift during training. We further decouple the representation space from the optimization space with a lightweight specialization projection, allowing task-specific adaptation without directly overspecializing the representations used at test time. \emph{TACO} establishes state-of-the-art performance on diverse benchmarks under cross-dataset and base-to-novel settings. Code will be released.

NeurIPS 2026

T2V-AttnDisrupt: Inducing Hallucinations in LVLMs via Misrouting Visual Evidence Retrieval

Yuran Bian, Xiaoyan Wang, Conghui Zheng, Xiaohan Zhang, Li Pan

Large vision-language models (LVLMs) ground language generation on visual content through the text-to-image slice of self-attention, which acts as a prompt-conditioned router for selecting visual evidence. To induce hallucinations in LVLMs, existing adversarial attacks largely operate at the two ends of this pipeline, either perturbing the front-end visual representation or optimizing against output-token objectives. This leaves the intermediate evidence-selection step as an underexplored yet low-cost attack surface, since it does not require heavy semantic manipulation of image features or extensive output-token optimization. To exploit this attack surface, Text-to-Visual Attention Disruption (T2V-AttnDisrupt) is proposed as an untargeted adversarial attack that induces hallucination by optimizing the input image to distort the text-to-image attention distribution relative to its clean reference, without relying on output-tokens. Experiments on four open-source LVLMs show that T2V-AttnDisrupt increases hallucination rates on captioning benchmarks and reduces VQA accuracy, while preserving overall response quality. It transfers across surrogate–target pairs and generalizes from a single captioning prompt to unseen VQA questions. Moreover, it remains effective against representative defenses, including encoder-level robustness, alignment-based fine-tuning, decoding-time hallucination mitigation, and attention-level interventions, indicating that text-to-image attention is still insufficiently protected. Mechanism analyses show that restoring the clean attention pattern largely recovers visual faithfulness, even when the adversarial image is kept fixed, indicating that hallucination can be driven by corrupted evidence routing rather than feature-level corruption. This low-cost and largely unprotected routing step calls for defenses that explicitly safeguard prompt-conditioned text-to-image attention.

NeurIPS 2026

T-ReX: Learning Tile-Reuse Indexes for Structured Model Compression

Haoyi Yang, Simon Kohaut, Zihan Ye, Devendra Singh Dhami, Kristian Kersting

The rapid proliferation of large-scale machine learning models, such as LLMs, has driven remarkable progress across application domains. Nevertheless, their scale comes with significant deployment challenges and inherent redundancies that remain open challenges to this day. To this end, we propose the Tile-Reuse Index (T-ReX), a structured model compression method that identifies and indexes reusable, contiguous parameter groups (tiles) across a model's architecture. By learning a compact set of matching tiles, we compress the model's memory footprint while preserving its performance. Furthermore, by reconstructing dense layers on the fly at inference time, T-ReX compressed models remain efficient at runtime. In our experiments, we show that T-ReX outperforms existing compression methods across benchmarks by most closely matching the original model's performance. We furthermore show how post-training on top of T-ReX enables small footprint models to recover most of the performance loss introduced by compression.

NeurIPS 2026

T$^2$-Splat: Adaptive Topology Mesh Splatting with Texture Residuals

Zhihao Tang, Youjia Zhang, Mingbo Zhao, Wei Yang

Triangle-based splatting has emerged as a promising bridge between high-quality novel view synthesis and traditional graphics pipelines. However, naively applying unstructured splatting mechanisms to polygonal primitives fails to exploit their inherent topological advantages, leading to over-tessellation and degraded high-frequency appearances. To address, we present T$^2$-Splat, a mesh splatting framework with adaptive topology and texture optimization. We introduce progressive edge-collapse and vertex-split operations to adaptively allocate triangle primitives, reducing face count while preserving well-conditioned connectivity. We further propose a scale-aware residual Mip-texture model to decouple appearance from geometry, for providing the topology with flexibility needed to safely collapse redundant triangles without introducing blurring or aliasing. Experiments on the Mip-NeRF 360, Tanks \& Temples, and DTU benchmarks demonstrate that T$^2$-Splat improves PSNR by +0.87 dB and maintains robust visual fidelity even under aggressive mesh compression to 10\% of the original face count.

NeurIPS 2026

S²MoE: Shared-Subspace Mixture of Sparse Experts

Feihong He, Anke Tang, Enneng Yang, Hao Jiang, Guojie Zhu, Gang Li, Xiaochun Cao, Li Shen

Model merging offers a training-free paradigm for integrating multiple specialized models into a unified multi-task system, enabling efficient knowledge reuse from models. However, parameter interference remains a critical challenge, limiting the scalability and efficacy of merged models. SVD-based merging techniques represent the current state-of-the-art, excelling in alleviating interference through task-specific knowledge extraction and subspace orthogonalization. % due to aggressive parameter truncation Despite these advances, they inevitably incur performance degradation due to aggressive parameter truncation, which discards valuable information and hinders inference accuracy. Our analysis reveals this truncation-induced knowledge loss as the fundamental bottleneck, motivating the need for mechanisms that preserve and recover discarded expertise without retraining. To address this, we introduce S MoE, a novel framework that augments SVD-based merging with a mixture of sparse experts to refine the truncation gap. S MoE comprises three key components: (1) a shared module that aggregates multi-task knowledge, (2) sparse experts that selectively recover truncation knowledge, and (3) a subspace mapping router to achieve precise training-free routing. Extensive experiments across vision and language benchmarks demonstrate up to 1.6% and 1.2% performance gains over SOTA methods, effectively validating robust and scalable model merging.

NeurIPS 2026

Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models

Xiangwen Wang, Ananth Balashankar, Varun Chandrasekaran

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law framework for jailbreaks by treating each attack as a compute-bounded optimization procedure and measuring progress on a shared FLOPs axis. Our systematic evaluation spans four representative jailbreak paradigms, covering optimization-based attacks, self-refinement prompting, sampling-based selection, and genetic optimization, across multiple model families and scales on a diverse set of harmful goals. We investigate scaling laws that relate attacker budget to attack success score by fitting a simple saturating exponential function to FLOPs--success trajectories, and we derive comparable efficiency summaries from the fitted curves. Empirically, prompting-based paradigms tend to be the most compute-efficient compared to optimization-based methods. To explain this gap, we cast prompt-based updates into an optimization view and show via a same-state comparison that prompt-based attacks more effectively optimize in prompt space. We also show that attacks occupy distinct success--stealthiness operating points with prompting-based methods occupying the high-success, high-stealth region. Finally, we find that vulnerability is strongly goal-dependent: harms involving misinformation are typically easier to elicit than other non-misinformation harms.

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 →