paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

NeurIPS 2026

Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency

Ziqi Wen, Parsa Madinei, Miguel Eckstein

Evaluating whether large vision-language models (VLMs) align with human perception for high-level semantic scene comprehension remains a challenge. Traditional white-box interpretability methods are inapplicable to closed-source architectures and passive metrics fail to isolate causal features. We introduce Counterfactual Semantic Saliency (CSS). This black-box, model-agnostic framework quantifies the importance of objects by measuring the semantic shift induced by their causal ablation from a scene. To evaluate AI-human semantic alignment, we tested prominent VLMs against a human psychophysics baseline comprising 16,289 valid responses across 307 complex natural scenes and 1,306 high-fidelity counterfactual variants. Our analysis reveals a pervasive scene comprehension gap: models exhibit an overreliance (relative to humans) on large objects (size bias), objects at the center of the image (center bias), and high saliency objects. In contrast, models rely less on people in the scenes than our human participants to describe the images. A model’s size bias is a primary driver explaining variations in model-human semantic divergence.

NeurIPS 2026

Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking

Haoyang Luo, Linwei Tao, Jie Gui, Xinghao Chen, Chang Xu, Jianyuan Guo, Minjing Dong

Multimodal Large Language Models (MLLMs) suffer from hallucinations, creating a critical need for Uncertainty Quantification (UQ) to ensure reliable deployment. However, existing approaches struggle to detect uncertainty caused by superficial associations, especially when the query-relevant signal is weak. We mainly attribute this issue to their bias toward aleatoric uncertainty arising from data ambiguity, overlooking epistemic uncertainty stemming from model limitations. To further decompose uncertainty types for a comprehensive UQ, we propose Causal-Invariant Masking (CIM), which measures the semantic shift between the original predictions and those conditioned on a causally-focused view. Based on this framework, we introduce Semantic Divergence as our core metric for UQ and provide theoretical evidence that it converges to the variance of model's sensitivity to non-causal correlations, establishing its ability to capture MLLM's limitation. To accelerate UQ in MLLMs, we further propose Expected Embedding Drift (EED), a fast geometric proxy metric that estimates semantic shift directly within the hyperspherical embedding space. Experiments show that our method achieves state-of-the-art performance on various benchmarks, while the proposed EED accelerates by nearly 50\% with comparable performance.

NeurIPS 2026

Reusable Conditional Resampling via Flow Matching for Constraint-Based Causal Discovery

SHUNYU ZHAO, Yanfeng Yang, Shuai Li, Kenji Fukumizu

Constraint-based causal discovery requires a large number of conditional independence (CI) tests. In nonlinear and high-dimensional settings, generative CI methods offer strong expressive power, but often suffer from high per test cost and limited reusability across the many query dependent conditional resampling tasks arising in graph search. We propose a generative nonlinear CI testing and graph search framework for PC-style causal discovery. First, we develop the Flow Matching based Conditional Independence Test (FMCIT), which combines joint flow matching modeling with conditional imputation to reformulate generative CI testing from query specific conditional modeling into a conditional resampling process that can be reused across queries. This allows the same generative model to repeatedly generate the randomized copies required by CI testing throughout the entire graph search procedure. We then introduce GPC‑FMCIT, which embeds FMCIT into a guided PC pipeline with screening, guidance, refinement, and orientation. By using low-cost screening to shrink the search space, constructing edge-specific candidate conditioning sets from local graph structure, and invoking FMCIT only in a budget-controlled refinement stage, GPC-FMCIT reduces both the deployment cost of individual nonlinear CI queries and the overall query complexity. Experiments on synthetic datasets and real-data analyses show that the proposed method achieves a strong accuracy--efficiency trade-off under nonlinear and high-dimensional structures. Overall, our results suggest that, through the joint design of reusable conditional resampling and controlled graph search, generative nonlinear CI testing can become a practical system level module for high‑dimensional PC‑style causal discovery.

NeurIPS 2026

Return to Basics: Very Simple Graph Contrastive Learning via Noise Cancellation Principle

Yanan Zhao, Feng Ji, Jingyang Dai, Jiaze Ma, Wee Peng Tay

Graph Contrastive Learning (GCL) has shown strong promise for unsupervised graph representation learning, yet its effectiveness remains limited on heterophilic graphs, where connected nodes often belong to different classes. Existing methods rely on complex augmentation schemes, intricate encoders, or negative sampling, which raises the question of whether such complexity is truly necessary in this challenging setting. In this work, we revisit the foundations of supervised and unsupervised learning on graphs and uncover a simple yet effective principle for GCL: mitigating node feature noise by aggregating it with structural features derived from the graph topology. This phenomenological study suggests that the original node features and the graph structure naturally provide two complementary views for contrastive learning. Building on this insight, we propose an embarrassingly simple GCL model that uses a GCN encoder to capture structural features and an MLP encoder to isolate node feature noise. Our design requires neither data augmentation nor negative sampling, yet achieves state-of-the-art results on heterophilic benchmarks with minimal computational and memory overhead, while offering advantages in homophilic graphs in terms of complexity, scalability, and robustness. Moreover, a variant of GCN-MLP based on the same principle also achieves SOTA performance on homophilic datasets. We provide theoretical justification for our approach and validate its effectiveness through extensive experiments.

NeurIPS 2026

Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS

Chaeeun Kim, Seungone Kim

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in multi-step reasoning and calling search engines at appropriate steps. However, existing retrieval-augmented reasoning approaches rely on separate retrieval models, limiting the LRM's role in retrieval to deciding when to retrieve and how to formulate queries, even with its inherent ability to handle vast knowledge spaces. This structural separation induces a representation bottleneck, as the retriever’s latent space often lacks the expressive granularity required to satisfy the generator’s sophisticated information needs. To address this, we shift our perspective on retrieval from sequence-to-sequence matching for all corpora to locating the answer-containing paths within the corpus, and propose a novel framework called FREESON (Retriever-FREE Retrieval-Augmented ReaSONing). This framework enables LRMs to directly access external knowledge by acting as both a generator and a retriever. To achieve this, we introduce a variant of the MCTS algorithm specialized for the retrieval task, which we call CT-MCT (Corpus-Traversing Monte Carlo Tree Search). Through this algorithm, the LRM selectively references specific segments identified during traversal, instead of fetching a fixed top-k set. Experiments on five open-domain QA benchmarks covering both single-hop and multi-hop questions demonstrate that FREESON achieves an average improvement of 14.4% in EM and F1 over four multi-step reasoning models with a separate retriever, and it also performs comparably to the strongest baseline, surpassing it by 3% on PopQA and 2WikiMultihopQA, and by 12% on the fact-checking benchmark FEVER.

NeurIPS 2026

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

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

Maintaining long-term geometric consistency remains a key challenge in long-horizon autoregressive video generation. Recent memory-augmented generative models address this issue by retrieving historical frames beyond the limited temporal context, but their effectiveness depends on two key design choices: what 3D-geometric evidence should represent past observations, and how memory frames should be selected from this evidence. Existing methods often rely on camera poses or field-of-view overlap, which are lightweight but too coarse to reason about pixel-wise visibility, or use explicit 3D reconstruction, which provides fine-grained evidence but is costly to maintain over long rollouts. We propose Coverage-Maximizing Retrieval-Augmented Generation (COVRAG), a depth-based memory retrieval framework that uses pretrained 3D priors to construct a target-view coverage map as lightweight 3D memory evidence. For frame selection, COVRAG maximizes residual coverage gain, iteratively retrieving frames that explain target-view regions not covered by the current context or previously selected memories. To improve scalability in long-video generation, we introduce a sliding-window depth caching for efficient geometry estimation. Experiments on RealEstate10K and DL3DV show that \modelname improves long-horizon geometric consistency while maintaining low latency compared to baselines.

NeurIPS 2026

Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks

Maximilian Schlegel, Rajai Nasser, Seijin Kobayashi, Yanick Schimpf, Oliver Sieberling, Robert Obryk, Kazuki Irie, Joao Sacramento, Johannes von Oswald

We investigate a general-purpose layer for deep learning that, instead of compressing arbitrary-size training data into fixed-size weight matrices, stores a new pair of key-value representations for every data point during training, and retrieves and recombines these representations through an attention mechanism at inference time---resulting in a growing neural net (NN). We derive such a "retrieval-centric deep learning" (RCDL) paradigm from the classic duality of a linear layer trained by gradient descent as a type of linear attention (LA) over the training data points---which motivates us to replace the corresponding LA by a more powerful form of attention from recent work on sequence models, namely, kernelized attention using radial basis function (RBF) and softmax-like kernels, as well as more advanced linear attention variants such as MesaNet and DeltaNet. We theoretically derive learning algorithms for the growing layers with kernelized attention, and empirically demonstrate their promising performance and sample-efficiency on classic image classification tasks and synthetic teacher-student learning datasets. In the MesaNet/DeltaNet-inspired extensions, we show a formal connection to a recently proposed optimizer and derive highly sample-efficient optimizers for conventional fixed-size NNs. Despite open challenges, RCDL represents a promising paradigm for nonparametric machine learning.

NeurIPS 2026

Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios

Kelvin J.L. Koa, Xinyang Li, Ke-Wei Huang

In this work, we study portfolio optimization under the stochastic discount factor (SDF) framework by learning market state representations that capture the underlying risk structures of financial data. This is challenging due to several factors: financial markets exhibit non-stationary dynamics with shifting regimes, multimodal inputs such as price and news data often contain stochastic noise, and existing diffusion-based approaches, while effective for modeling stochastic dynamics, rely on assumptions such as isotropic Gaussian noise that fail to capture the state-dependent nature of financial uncertainty. To address these challenges, we introduce RADAR, a retrieval-augmented diffusion framework that learns market representations by conditioning on similar historical regimes. RADAR leverages retrieval to construct context-dependent noise distributions, applies conditional diffusion to denoise multimodal representations, and initializes the diffusion process using empirical statistics to reflect state-dependent uncertainty. Experiments show that RADAR achieves state-of-the-art performance on key risk-adjusted metrics while producing economically meaningful signals on asset returns and correlations.

NeurIPS 2026

Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection

Christos Panourgias, Roberto Stanzione, Adrien Petralia, Themis Palpanas, Paul Boniol

Anomaly detection is a fundamental task for time-series analytics, with important implications for the downstream performance of many applications. Despite the large number of anomaly detection methods proposed in the literature, recent benchmark studies have shown that no single detector performs best across highly heterogeneous time series. Therefore, a practical and scalable solution is to develop a model-selection method that, for a given time series, selects the anomaly detector most likely to perform well. Nevertheless, the model selection approach proposed in the literature suffers from a significant drop in accuracy when applied in Out-of-Distribution (OOD) settings. In this paper, we tackle the aforementioned limitation and propose \textbf{\textsc{RAMSAD}}, a train-free, retrieval-based framework for model selection in time-series anomaly detection. Given a new time series, our method queries a knowledge base of previously observed instances, retrieves the top-${k}$ most similar series, and transfers detector recommendations from their performance profiles. The framework can operate with standard similarity measures as well as embedding-based representations. Overall, we demonstrate that similarity-based retrieval constitutes a strong and efficient foundation for model selection in time-series anomaly detection.

NeurIPS 2026

Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information

Chanho Park, Daehyeon Choi, Jihyun Lee, Minhyuk Sung

Vision-language models (VLMs) can locate an image region referred to by a text prompt and route the corresponding visual evidence to the output, yet the internal mechanism behind this behavior is not understood. Inspired by retrieval heads in large language models, we ask whether VLMs contain an analogous mechanism for visual retrieval. We answer affirmatively by introducing Visual Retrieval Heads(VRHs), a small subset of attention heads (about 1.7–2.6%) that are causally responsible for grounding text descriptions to image regions. To find them, we recast existing head-scoring methods under a unified design space over query tokens, key aggregation, and cross-sample aggregation. We then show that scoring attention from output prediction tokens with a sum over the ground-truth referent region most reliably identifies causal heads. Across four VLMs and five referring-expression benchmarks, masking only the top 20 VRHs reduces grounding accuracy by up to 80 percentage points, while masking the same number of random heads has little effect. Beyond replicating the causal-sparse-universal triad established for text retrieval heads, VRHs exhibit several properties not previously reported: they generalize across visual reference tasks, remaining causal on attribute, spatial, counting, and visual-math benchmarks despite being discovered through bounding-box prediction; they are functionally specific, preserving output format while corrupting localization; and they are architecturally shared, transferring causally across VLMs that share an LLM backbone but differ in vision encoder, projector, and instruction tuning

NeurIPS 2026

Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction

kejun ren, Lei Jin, Tianxin Huang, Lianming Xu, LI Wang

Streaming 3D reconstruction under a strict constant-memory budget hinges on how the recurrent state is updated as the stream evolves. We profile TTT3R-style per-token gates across five benchmarks and discover a structural bottleneck: the gate is intrinsically bounded in magnitude (median $0.31$; never exceeding $0.6$) and nearly frame-invariant, yielding an effective memory horizon of only $\sim$3 frames per state token, which serves as the structural origin of long-sequence drift. We trace this to a missing axis: existing inference-time methods modulate updates only at the per-token, intra-frame level, while the orthogonal frame-level question of \emph{how strongly each frame should contribute to the state} has been silently treated as content-independent. We close this gap with a scalar frame-level gate $\alpha_t \in (0, 1]$ derived in closed form from frame-to-frame changes of internal features---a continuous relaxation of classical SLAM keyframe selection that requires no parameters, no training, and no extra forward pass. Across six benchmarks spanning camera pose, video depth, and 3D reconstruction at sequence lengths up to $4,541$ frames, our gate cuts ATE by $51\%$ on long TUM-RGBD pose sequences, reduces AbsRel by $12.8\%$ on Bonn video depth, and on KITTI long-sequence pose estimation surpasses LongStream and Keyframe-VO which are specially constructed for long sequences via retraining and policy learning, while retaining strictly constant memory at zero training cost.

NeurIPS 2026

Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection

Manni Cui, Ziheng Qin, ZiAn Wang, Ruiqi Liu, Dianyuan Zou, Jianglan Wei, Han Zhou, Yu Liu, Xu Jingrui, Wenhao Wang, Zhenyu Zhang

AI-generated videos (AIGVs) typically contain subtle temporal artifacts that arise from inter-frame inconsistencies rather than within individual frames. A detector that captures such artifacts should therefore benefit from video pretrained backbones over image only ones. In practice, however, video backbones with standard global readouts often fail to outperform strong image pretrained probes on AIGV benchmarks. We attribute this gap to excessive spatiotemporal aggregation in the readout. Video pretrained backbones tend to compress each frame into a single global descriptor. This compression suppresses local patch level temporal dynamics and discards inter patch relations, which are precisely the cues that AIGV detection most reliably depends on. Based on this, we propose Velocity Gated Patch Velocity Profiling (V-PVP), a lightweight readout that replaces only the aggregation layer with two parallel streams over the patch velocity field, adding only about $0.5$M trainable parameters. V-PVP serves as a general plug-and-play module that consistently improves performance across diverse video backbones under both end-to-end fine-tuning and linear probing settings. Our method reaches \textbf{95.28} AUC on AIGVDBench while keeping the backbone fully frozen. The results show that simply replacing the aggregation layer reactivates the temporal potential of frozen video backbones, restoring their advantage on AIGV detection. Code is available at https://anonymous.4open.science/r/PVP-81B3/.

NeurIPS 2026

Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding

Zhongxing Xu, Zhonghua Wang, Zhe Qian, Shiyan Su, Ming Hu, Xiaocheng Zou, Wei Feng, Mingquan Lin, Yuyin Zhou, Yifan Peng, Hamid Rezatofighi, Zongyuan Ge

Recent advancements in multimodal diffusion language models (MDLMs) have exhibited strong global modeling capabilities through iterative refinement. We observe that mask uncertainty follows an overall downward trend during iterative denoising, while a few denoising steps exhibit localized entropy spikes closely associated with hallucinations. We argue that anomalous steps can be identified by measuring the entropy deviation of each denoising step from its neighboring temporal window. We hypothesize that discrete token commitment discards the distributional information at masked positions, limiting the continued interaction between candidate semantics and the context during entropy spikes. With this goal, we present StepRefine, a plug-and-play decoding strategy that leverages semantic context to achieve reliable denoising. The core of our method lies in a step-aware switch between discrete denoising and latent refinement. The model employs probability-weighted embeddings at entropy spike steps to preserve diverse reasoning hypotheses and performs multiple rounds of continuous refinement. Meanwhile, a refinement controller monitors distributional stability to reduce unnecessary loops and switch the model back to standard discrete denoising. Through extensive experiments, StepRefine demonstrates significant hallucination mitigation across different MDLMs on multimodal benchmarks.

NeurIPS 2026

Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings

Inês Oliveira e Silva, Sérgio Jesus, Iker Perez, Rita P. Ribeiro, Carlos Soares, Hugo Ferreira, Pedro Bizarro

Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented landscape with little consensus on practical deployment. While theoretical differences are well-documented, evaluation remains reliant on quantitative proxies whose alignment with human utility is unverified. In this work, we use a unified amortized framework to isolate semantic differences between eight Shapley variants under the low-latency constraints of operational risk workflows. We conduct a large-scale empirical evaluation across four risk datasets and a realistic fraud-detection environment involving professional analysts and 3,735 case reviews. Our results reveal a fundamental misalignment: standard quantitative metrics, such as sparsity and faithfulness, are decoupled from human-perceived clarity and decision utility. Furthermore, while no formulation improved objective analyst performance, explanations consistently increased decision confidence, signaling a critical risk of automation bias and overconfidence in high-stakes settings. These findings demonstrate that current evaluation proxies are insufficient for predicting human impact, motivating our release of interaction measurements to support research into behaviorally grounded XAI evaluation.

NeurIPS 2026

Rethinking Vector Field Learning for Generative Segmentation

Chaoyang Wang, Yaobo Liang, Boci Peng, Fan Duan, Yunhai Tong

Taming diffusion models for generative segmentation has attracted increasing attention. While existing approaches primarily focus on architectural tweaks or training heuristics, there remains a limited understanding of the intrinsic mismatch between continuous flow matching objectives and discrete perception tasks. In this work, we revisit diffusion segmentation from the perspective of vector field learning. We identify two key limitations of the commonly used flow matching objective: gradient vanishing and trajectory traversing, which result in slow convergence and poor class separation. To tackle these issues, we propose a principled vector field reshaping strategy that augments the learned velocity field with a detached distance-aware correction term. This correction introduces both attractive and repulsive interactions, enhancing gradient magnitudes near centroids while preserving the original diffusion training framework. Furthermore, we design a computationally efficient, quasi-random centroid encoding scheme inspired by Kronecker sequences, which integrates seamlessly with an end-to-end pixel neural field framework for pixel-level semantic alignment. Extensive experiments consistently demonstrate significant improvements over vanilla flow matching approaches, substantially narrowing the performance gap between generative segmentation and strong discriminative specialists.

NeurIPS 2026

Rethinking Time Series Tokenization from a Frequency Perspective

Zelong Tian, Ming Jin, Bo Du, Shirui Pan

Tokenization that partitions time series into subsequences has become a foundational paradigm in modern time series modeling. However, we find that current tokenization strategies inherently introduce spectral distortions, forcing the learned representations to diverge from the true underlying patterns such as trend, periodicity, and seasonality, thereby impairing model performance. Through theoretical analysis from a frequency perspective, we derive the boundary conditions under which such distortions occur. To overcome this distortion, we propose **TimeFT**, a nearly distortion-free frequency-based tokenizer for time series data. TimeFT obtains tokens through frequency-domain partitioning, frequency shifting, and Nyquist sampling. The method is parameter-free, incurs negligible computational complexity, and can serve as a drop-in replacement for existing tokenizers. Our extensive experiments on diverse tasks such as forecasting, classification, and anomaly detection demonstrate that TimeFT consistently and significantly improves performance.

NeurIPS 2026

Rethinking State Tracking in Recurrent Models Through Error Control Dynamics

Jiwan Chung, Heechan Choi, Seon Joo Kim

The theory of state tracking in recurrent architectures has predominantly focused on expressive capacity: whether a fixed architecture can theoretically realize a set of symbolic transition rules. We argue that equally important is error control, the dynamics governing hidden-state drift along the directions that distinguish symbolic states. We prove that affine recurrent networks, a class of models encompassing State-Space Models and Linear Attention, cannot correct errors along state-separating subspaces once they preserve state representations. Consequently, practical affine trackers do not learn robust state tracking; rather, they learn finite horizon solutions governed by accumulated state-relevant error. We characterize the mechanics of this failure, showing that tracking remains readable only while the accumulating within-class spread remains small relative to the initial between-class separation. We demonstrate empirically on group state-tracking tasks that this breakdown is predictable: tracking collapses when the distinguishability ratio crosses the readability threshold of the trained decoder. Across trained models, the point of this crossing predicts the horizon at which downstream accuracy fails. These results establish that robust state tracking is determined not only by an architecture's theoretical expressivity but crucially by its error control.

NeurIPS 2026

Rethinking Softmax Attention: Polynomial Activations for Transformers

Hemanth Saratchandran, Jianqiao Zheng, Yiping Ji, Wenbo Zhang, Simon Lucey

Softmax attention is typically viewed as effective because it produces a normalized probability distribution over input tokens. In this paper, we challenge this view by showing that a key mechanism behind softmax attention is its implicit control of the Frobenius norm of the attention matrix, which stabilizes training. Motivated by this observation, we study alternative attention activations, focusing on polynomial maps that provide a similar regularization effect without satisfying the usual softmax constraints. Our theoretical analysis shows that certain polynomial activations can replace softmax despite violating positivity, row-wise normalization, and sparsity. Extensive experiments across transformer applications show that these alternatives achieve strong performance, suggesting that the success of softmax attention is not inherently tied to its probabilistic interpretation.

NeurIPS 2026

Rethinking Sequential Locate-Then-Edit: Optimality and Stability

Bingqing Liu, Wei Liu, Zhiying Deng, Jun Wang, Yuhua Li, Ruixuan Li

The \textit{Locate-Then-Edit} framework enables efficient knowledge updates in large language models without requiring full retraining. Recent research has increasingly focused on \textit{sequential editing}, where knowledge arrives continuously and the model is updated incrementally. However, existing sequential methods commonly suffer from catastrophic forgetting and model collapse after only a few hundred edits. In contrast, \textit{batch editing}---which performs joint optimization over all edits and represents the theoretical optimum---can support tens of thousands of edits with high edit efficacy while preserving the model's general capabilities, resulting in a substantial performance gap between the two editing paradigms. In this paper, we demonstrate that this gap can be closed via a \textit{batch-equivalent sequential editing} approach. Moreover, we investigate the underlying mechanism of model degradation in existing sequential methods by analyzing the convergence behavior of weight perturbations as edits accumulate. Our analysis reveals that current methods typically exhibit linear or logarithmic growth in perturbation, whereas the proposed batch-equivalent method achieves \textit{time-invariant} growth, thereby theoretically guaranteeing long-term stability and preserving the integrity of pretrained knowledge throughout massive-scale sequential editing.

NeurIPS 2026

Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment

Yuqing Liu, Huiyuan Chen, Yibo Wang, Wooseong Yang, Philip S. Yu

Semantic ID-based generative recommendation represents each item as a sequence of discrete tokens, enabling structured modeling of item semantics. A critical challenge is constructing semantic IDs that are both semantically expressive and computationally efficient. While recent approaches favor complex learned quantization, simple hashing-based methods such as SimHash are widely regarded as fundamentally inferior. In this work, we challenge this consensus by showing that the apparent performance gap does not stem from inherent limitations of hashing, but rather from a structural mismatch with autoregressive decoding, coupled with the inevitable information loss during rigid discretization. Based on this insight, we propose FLASH, a two-stage framework that revitalizes training-free SimHash tokenization through parallel decoding and explicit semantic alignment. Despite its simplicity, FLASH achieves state-of-the-art performance across multiple datasets without requiring any tokenizer training, while exhibiting stronger generalization in cold-start scenarios. Notably, we demonstrate that semantic alignment acts as a universally effective mechanism across diverse paradigms. Our findings suggest that, with compatible decoding and semantic grounding, simple and efficient tokenizers can outperform complex learned counterparts. Our code and data are available: https://anonymous.4open.science/r/Flash-014A/.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.