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

Scaffold3D: SfM-Conditioned Pointmap Prediction for Multi-View 3D Reconstruction

Frano Rajič, Yutong Chen, Haofei Xu, Zador Pataki, Marc Pollefeys, Siyu Tang

Multi-view 3D reconstruction is increasingly driven by feed-forward models, which are fast and robust but often imprecise or globally inconsistent across views, especially in sparse-view and low-overlap settings. Structure-from-motion (SfM) offers a complementary geometric signal through camera poses and sparse 3D points estimated by correspondence filtering and optimization. To propagate this globally consistent \emph{SfM scaffold} into dense geometry, we introduce \textbf{Scaffold3D}, an SfM-conditioned reconstruction framework that injects image patch-aligned SfM point tokens into a pairwise feed-forward pointmap predictor. Our approach preserves image-token reasoning while using explicit SfM structure to condition dense prediction. Since pairwise pointmaps are predicted in local frames, we fuse them with global alignment and an SfM anchoring term. Across established benchmarks (ScanNet++, ETH3D, and Tanks\&Temples) and out-of-domain data (4D-DRESS and MV-dVRK), Scaffold3D achieves stronger overall performance than feed-forward reconstruction models, point-token propagation, depth-completion baselines, and recent geometry-conditioned models. The gains are especially clear in low- and no-overlap evaluations. Our two-view SfM-conditioned pointmap predictor also outperforms several multi-view geometry-conditioned baselines, indicating that how geometric inputs are fused with image-token reasoning is as important as the number of conditioned views. Together, these results establish SfM-scaffold conditioning as a practical interface between learned pointmap prediction and classical geometric optimization.

NeurIPS 2026

Say the Same, Act Differently: Text-Orthogonal Action Subspaces in Reasoning Vision-Language-Action Models

Zihao Feng, Qingzhao Zhang, Chunyu Xia, Bo Yu, Zhuoqing Morley Mao, Ramesh Govindan

Vision-language-action (VLA) policies increasingly generate natural-language rationales before executing embodied actions. These rationales are attractive as monitors for safety-critical behavior because users or automated checkers can inspect whether the model appears to understand the scene and intend a safe action before execution. We show that this signal can be misleading. In many reasoning VLAs, the rationale generator and action head share continuous hidden states, while the generated text reveals only part of that representation. This creates a Say the Same, Act Differently failure mode, where rationale text remains stable while the action output changes substantially. We first study this phenomenon by introducing a new statistical method to separate text-sensitive and action-sensitive directions in hidden-state space of a reasoning VLA. Across the driving VLA Alpamayo and the manipulation VLA InstructVLA, we show that the dominant action direction lies largely outside the active text span, with mean projection ratios of only 1.9% and 5.3%. We define the residual as a text-neutral action-subspace (TNAS) direction, which tests whether action-relevant directions remain after removing measured text-sensitive directions. We then use TNAS to guide white-box pixel-space projected-gradient-descent (PGD) attacks on Alpamayo. TNAS-guided PGD successfully uses a localized two-forward-camera patch to induce a 30.5 m mean ADE shift in trajectory planning while preserving the exact rationale in 86.7% of cases. Moreover, across multiple text-preserving PGD objectives, the optimization direction consistently aligns with TNAS. These results reveal a fundamental shared-cache monitorability gap in reasoning VLAs: stable rationale text should not be treated as sufficient evidence that the action output remains stable.

NeurIPS 2026

SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery

Jiajun Jiang, Chunliang Hua, Zichun Chen, Yanxing Wu, Zeyuan Yang, Jie Song, Xiao Hu

Urban uncrewed aerial vehicle (UAV) vision-language navigation (VLN) requires agents to follow instructions across extended urban spaces, inherently demanding long-term memory and geospatial grounding. However, scaling existing benchmarks remains difficult because of their reliance on costly reconstructed 3D assets, limiting geographic diversity and episode scale. To address this, we introduce SatNav, a scalable, long-horizon UAV VLN benchmark built from high-resolution satellite imagery. SatNav targets city-level navigation missions and uses satellite crops as approximations of UAV nadir views for visual observations. Through an automated cue-to-episode pipeline, SatNav constructs 118K episodes from 59 scenes across 18 cities, with an average trajectory length of 379 m. To stress-test long-horizon memory and geospatial reasoning, SatNav defines three task families: Boundary, Landmark, and Route, targeting loop progress tracking, landmark-based spatial grounding, and route following with counting cues. Benchmarking classical and recent large vision language model (LVLM) based VLN agents on SatNav shows that city-scale navigation remains challenging. We further introduce SwiftVLN, a modular framework with switchable memory components, and conduct systematic memory-design ablations. Finally, satellite-to-UAV transfer experiments show that satellite-trained navigation models can operate on real-flight UAV observations, showing the practical relevance of SatNav.

NeurIPS 2026

SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception

Yiyang Su, Jie Zhu, Feng Liu, Anil Jain, Xiaoming Liu

While foundation models have significantly advanced human recognition across diverse modalities, they predominantly rely on static, geometric feature extraction. This approach fundamentally diverges from human perception. Consequently, current models often suffer from ``semantic blindness,'' overfitting to transient noise while failing to leverage invariant soft biometrics, and struggle to capture temporal motion signatures. To bridge this gap, we propose SapiensID 2.0, a human recognition framework enriched with both semantic and temporal awareness. To overcome the lack of soft-biometric annotations, we transfer zero-shot semantic knowledge from Multimodal Large Language Models (MLLMs) into a discriminative embedding space. We resolve the dimensional mismatch between these spaces using Invariant Trait Alignment (ITA) to distill core persistent traits, and Transient Noise Disentanglement (TND) to decouple artifacts like clothing. Furthermore, we design a Kinematic Semantic Attention Head (K-SAH) that extends spatial attention across temporal windows. By tracking semantic patches over time, K-SAH captures rich kinematic signatures without requiring large-scale video datasets. Extensive experiments demonstrate that SapiensID 2.0 achieves state-of-the-art performance across image- and video-based person re-identification and gait recognition, while maintaining robust face recognition capabilities.

NeurIPS 2026

Sandboxed Coding Agents are Competitive Omni-modal Task Solvers

Dongping Chen, Xuanao Huang, Zhihan Hu, Qingyuan Shi, Dianqi Li, Tianyi Zhou

As multimodal LLMs increasingly emphasize video and audio, a common assumption is that solving such tasks calls for native omnimodal models. We show that this is not always necessary: coding agents equipped with only text+vision and a sandboxed tool-using interface can perform competitively with, and in several settings outperform, SOTA native omnimodal models and predefined multimodal agent scaffolds across multiple audio-video benchmarks. Our trajectory analysis suggests that their advantage comes from coding agents writing code and orchestrating tools to retrieve relevant content from transcripts, frames, and other non-textual modality signals from raw inputs. This effectively converts omnimodal tasks into evidence retrieval and information processing problems, avoiding the inefficiency of ingesting entire videos or audio streams into context. To characterize remaining limitations, we propose a failure taxonomy and a process-level analysis of tool-use traces, and find that simple skill injection, including human-written skills and self-distilled skills from execution logs, can substantially improve performance over the no-skill baseline. To examine whether such capability can be elicited in open-source models, we further introduce Code-X, a complete training recipe with the OmniCoding trajectory dataset and verifiable reward, providing an exploratory baseline on Qwen-3.5-9B and Qwen-3.6-27B. Finally, given the maturity of many-modality understanding, we argue that the more meaningful frontier lies in many-modality processing, and introduce TerminalBench-O, the first process-level benchmark designed for coding agents on real-world omnimodal processing tasks. Together, our findings open new directions for omnimodal content processing and evaluation.

NeurIPS 2026

Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation

Jan Schuchardt, Nikita Kalinin

We study privacy amplification for differentially private model training with matrix factorization under random allocation (also known as the balls-in-bins model). Recent work by Choquette-Choo et al. (2025) proposes a sampling-based Monte Carlo approach to compute amplification parameters in this setting. However, their guarantees either only hold with some high probability or require random abstention by the mechanism. Furthermore, the required number of samples for ensuring $(\epsilon,\delta)$-DP is inversely proportional to $\delta$. In contrast, we develop sampling-free bounds based on Rényi divergence and conditional composition. The former is facilitated by a dynamic programming formulation to efficiently compute the bounds. The latter complements it by offering stronger privacy guarantees for small $\epsilon$, where Rényi divergence bounds inherently lead to an over-approximation. Our framework applies to arbitrary banded and non-banded matrices. Through numerical comparisons, we demonstrate the efficacy of our approach across a broad range of matrix mechanisms used in research and practice.

NeurIPS 2026

Sampling-Based Safe Reinforcement Learning

Luca Vignola, Bruce D Lee, Manish Prajapat, Manuel Wendl, Melanie Zeilinger, Andreas Krause, Yarden As

Safe exploration remains a fundamental challenge in reinforcement learning (RL), limiting the deployment of RL agents in the real world. We propose _Sampling-Based Safe Reinforcement Learning_ (SBSRL), a model-based RL algorithm that maintains safety throughout the learning process by enforcing constraints jointly across a _finite_ set of dynamics samples. This formulation approximates an intractable worst-case optimization over uncertain dynamics and enables practical safety guarantees in continuous domains. We further introduce an exploration strategy based on constraining epistemic uncertainty, eliminating the need for explicit exploration bonuses. Under regularity conditions, we derive high-probability guarantees of safety throughout learning and a finite-time sample complexity bound for recovering a near-optimal policy. Empirically, SBSRL achieves safe and efficient exploration both in simulation and in real-world experiments, and readily extends to practical deep-ensemble implementations that scale to high-dimensional continuous control problems.

NeurIPS 2026

Sample-Efficient Optimization over Generative Priors via Coarse Learnability

Pranjal Awasthi, Sreenivas Gollapudi, Ravi Kumar, Kamesh Munagala

We study zeroth-order optimization where solutions must minimize a cost $d(s)$ while maintaining high probability under a complex generative prior $\mathcal{L}(s)$ (e.g., a parameterized model). This reduces to sampling from a target distribution proportional to $\mathcal{L}(s) e^{-T \cdot d(s)}$. Since classical model-based optimization (MBO) lacks finite-sample guarantees for expressive approximate learners, we introduce \emph{coarse learnability}, a flexible statistical assumption requiring only that a learned model covers the target's probability mass within a polynomial factor. Leveraging this assumption, we design an iterative MBO algorithm called ALDRIFT with a sample correction step that provably approximates the target using only a polynomial number of samples. We apply this framework to globally optimizing non-convex objectives bounded by a quadratic envelope in $\mathbb{R}^d$, where we show this assumption is naturally satisfied for a family of ``optimistic'' posterior distributions. To reach global $\varepsilon$-optimality, this implies a sample complexity of $\widetilde{O}(\log 1/\varepsilon)$, a rate characteristic of optimistic space-partitioning methods. We further justify coarse learnability as an assumption for generative priors theoretically, proving that in simple settings, parametric maximum likelihood estimation and over-smoothed kernel density estimators naturally satisfy it. Finally, one motivation for our framework comes from inference-time alignment. Though our primary contribution is formalizing the theoretical foundations of MBO, we provide qualitative evidence that, in simple settings, even primitive LLMs can shift their distributions toward lower-cost regions when fine-tuned with zeroth-order feedback.

NeurIPS 2026

Sample complexity of stochastic optimization with integer variables

Hongyu Cheng, Yinghao Zheng, Marco Molinaro, Amitabh Basu

We establish sample complexity results for stochastic optimization over the integers, especially with a view to understand the complexity with respect to the corresponding continuous optimization problem. We show that integer optimization can sometimes require strictly more samples and sometimes strictly smaller number of samples, depending on the structure of the objective and constraints. 1. For Lipschitz objectives over subsets of the $\ell_\infty$ ball, the statistical complexity of general stochastic mixed-integer, nonlinear, nonconvex optimization is exactly the same as stochastic linear optimization with just bound constraints. 2. For Lipschitz objectives over subsets of the $\ell_2$ ball, we show that integer optimization can require strictly *smaller* sample size compared to the continuous setting in a certain regime. To get to this result, we also establish tight sample complexity results for nonconvex continuous stochastic optimization which, to the best of our knowledge, do not appear in prior work. 3. For strongly convex, smooth objectives, integer optimization has high statistical complexity compared to the continuous setting. In particular, we show that integer optimization requires $\Omega(1/\epsilon^2)$ samples to report an $\epsilon$-approximate solution, compared to the well-known $O(1/\epsilon)$ sample complexity from the continuous optimization literature.

NeurIPS 2026

Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models

Zeyang Ding, Xinglin Hu, Jicong Fan

Hallucinations remain a major barrier to the trustworthy deployment of large language models (LLMs). We study hallucination detection from the perspective of prompt-conditioned response distributions. For a fixed prompt, an LLM induces a distribution over possible responses; when the model is uncertain or hallucinates, this distribution often becomes more complex and less internally consistent. However, this distribution is unknown, and its samples are variable-length token sequences rather than fixed-dimensional points, making direct complexity estimation difficult. To address this challenge, we propose a training-free detector based on sample-to-sample transform costs in representation space. Specifically, we represent each sampled response as an empirical distribution over generated-token hidden embeddings and compute pairwise Wasserstein distances between responses. The resulting Wasserstein distance matrix characterizes the cost structure of transforming one sampled response into another. From this matrix, we derive two complementary hallucination signals: \textbf{AvgWD}, which measures the average transform cost, and \textbf{EigenWD}, which captures the spectral complexity of the transform-cost structure. Importantly, we extend the proposed detector beyond white-box access by using an accessible auxiliary model to construct representation-space consistency signals for black-box LLMs, substantially broadening the practical applicability of our method. Experiments across five open-source LLMs and four benchmarks show that AvgWD and EigenWD consistently achieve competitive or superior AUROC compared with strong training-free uncertainty baselines. These results suggest that distributional complexity in token-level representation space provides an effective signal for hallucination detection.

NeurIPS 2026

Sample Size Design for Bounds on Discrete Probabilities of Causation

Tianyuan Cheng, Ruirui Mao, Judea Pearl, Ang Li

Probabilities of causation (PoCs), such as the probability of necessity and sufficiency (PNS), are important tools for decision making but are generally not point identifiable. Existing work has derived bounds for these quantities using combinations of experimental and observational data. However, there is very limited research on sample size analysis, namely, how many experimental and observational samples are required to achieve a desired margin of error. In this paper, we propose a sample-size design framework for PoC bounds that can be expressed as finite minima or maxima of smooth functions of experimental and observational probabilities — a representation that covers binary PNS, PN, and PS, as well as representative multi-valued PoC families recently shown to subsume the discrete PoC bounds in the current literature. Our framework gives endpoint-specific sample-size formulas that account for the joint covariance structure of the probability estimates: a distribution-free rule for affine bounds, and a pilot-based plug-in rule with theoretical safety guarantees for ratio-type bounds. Simulations show that the proposed rules achieve the target precision and coverage, recover a much smaller size requirement for binary PNS than the existing calculation, and provide sample-size designs for other discrete PoCs where no prior general sample-size formula is available.

NeurIPS 2026

Sample Efficient Generative Molecular Optimization with Joint Self-Improvement

Serra Korkmaz, Adam Izdebski, Jonathan Pirnay, Rasmus Møller-Larsen, Michal Kmicikiewicz, Pankhil Gawade, Maksim Pavlov, Dominik G Grimm, Ewa Szczurek

Generative molecular optimization aims to design molecules with properties surpassing those of existing compounds. However, evaluating candidate molecules is expensive, so sample efficiency, i.e., generating optimized molecules within a fixed evaluation budget, is essential. Moreover, in the offline setting, where a surrogate model approximates candidate evaluation, sample inefficiency compounds with surrogate error, further limiting performance. To address these challenges, we introduce Joint Self-Improvement (JSI), a framework for sample-efficient online and offline molecular optimization. JSI combines **(i) a joint generative-predictive model** trained via a joint likelihood-based loss, which aligns molecule generation and surrogate modeling, and **(ii) inference-time self-improvement**, which iteratively biases the generative component of the joint model toward higher-scoring molecules using direct objective evaluations in the online setting and the predictive component in the offline setting. Experiments across docking score optimization, in both online and offline settings, as well as antimicrobial peptide optimization, demonstrate that JSI outperforms state-of-the-art methods under limited evaluation budgets.

NeurIPS 2026

Same Words, Different Judgments: How Preferences Vary Across Modalities

Aaron Broukhim, Nadir Weibel, Eshin Jolly

Preference-based reinforcement learning (PbRL) is the dominant framework for aligning AI systems to human preferences. However, evaluation protocols for such data were designed for text and have not been validated for speech. We present the first ICC-based, controlled cross-modal study of human and synthetic preference annotations, comparing text and audio evaluations of identical semantic content across 100 prompts. We show that achieving $\textit{good}$ agreement within either modality (ICC(2,$k$) $\approx$ .80) requires $\sim$9 raters. At the same time, modalities show marked differences in how people report preferences: audio raters exhibit narrower decision thresholds, reduced length bias, and more user-oriented evaluation criteria, with near-chance cross-modality agreement. We demonstrate that synthetic ratings can be used to effectively predict inter-rater agreement, thus serving as an early signal for stimulus selection and proxy for human annotations. Together, these findings argue that evaluation protocols for audio preference data require modality-specific design rather than direct adaptation from text.

NeurIPS 2026

Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents

Ziming Li, Jiatan Huang, Xiaoguang Guo, Guiling &quot, Grace&quot, Wang, Chuxu Zhang

Adaptive test-time compute for LLM agents aims to invoke extra computation only when it improves performance. Existing methods typically use confidence-, uncertainty-, or difficulty-based gates, assuming a fixed direction from the gating signal through compute need to the value of computation. This makes gating a utility-calibration problem: gating signals should align with whether extra computation improves the final outcome over the base policy. We show that this alignment is unstable: the same signal predicts rollout benefit in one setting and rollout harm in another, with reversals across environments and backbones even when the task is fixed. Wrong-direction gates can therefore worsen performance by precisely selecting harmful states. This reversal reflects a deeper distinction between compute need and compute suitability: a high uncertainty signal may indicate decision-difficult states where rollouts help compare alternatives, or intervention-unsuitable states where the current context does not support useful rollout-based improvement. Under this two-source model, fixed-direction gates are unreliable across heterogeneous settings. To address this, we propose DIAL (**D**irection-**I**nformed **A**daptive **L**earning), a sparse gate trained from signal-agnostic counterfactual exploration to learn the utility direction of state features per (environment, backbone). Across six environments and three backbones, DIAL yields a stronger overall success-cost trade-off than fixed-direction baselines. Our code is open-sourced at [https://anonymous.4open.science/r/DIAL-2A7E/](https://anonymous.4open.science/r/DIAL-2A7E/).

NeurIPS 2026

Same Function, Different Mechanism: Implementation-Local Geometry Beyond Accuracy

Miroslav Lžičař

Two finite-domain implementations, including neural-network parameterizations restricted to an evaluation domain, can agree on every input while implementing the computation through different mechanisms, such as independent lookup storage or a shared reusable rule. We formalize this distinction as a statement about the local Kullback-Leibler geometry of an implementation chart: a mechanism-specified local family of perturbations around a fixed predictive distribution. For finite input-output distributions with full support, we prove a logit-Fisher pullback theorem: the Hessian rank of a chart equals the dimension of its tangent image in the quotient logit space, so the quadratic active contribution to the local learning coefficient is half this rank under the analytic/dead-kernel conditions stated below. We prove that this rank is invariant under local reparameterizations, dead parameters, and redundant duplications, but changes when the allowed perturbation class changes; hence it is a first-order chart-germ invariant, not a function-only invariant. For mechanisms specified by exact finite-group sharing, we give a closed-form orbit-count formula for the active dimension. Lookup and shared cyclic modular addition are then immediate corollaries: both implement the same softened conditional distribution, yet their active ranks are $p^2(p-1)$ and $p-1$, respectively. The results clarify when Bayesian/Singular-Learning-Theory complexity can distinguish extensionally equivalent algorithms and when chart dependence is a real modeling choice rather than a defect.

NeurIPS 2026

Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders

Chungpa Lee, Jihoon Kwon, Kyle Min, Jy-yong Sohn

Vision-language models map images and text into a joint embedding space. However, these embeddings often entangle multiple semantic features, which limits their interpretability and controllability. While sparse autoencoders have emerged as a useful tool for decomposing these embeddings into monosemantic features, their application to joint embedding spaces has largely relied on an implicit, untested assumption that semantically corresponding features share the same directions across modalities. In this paper, we challenge this assumption by identifying discrepancies in feature directions for the same concept across image and text modalities, a phenomenon we term *cross-modal feature heterogeneity*. We demonstrate that this heterogeneity is a key driver of the *modality split*, where a shared concept activates different latents depending on the modality. This finding further reveals why aligning latent activations alone is insufficient to resolve the underlying feature mismatch. To address this misalignment, we propose an approach that trains sparse autoencoders to preserve the unique feature geometry of each modality and aligns corresponding features post hoc. Our method improves reconstruction fidelity and enhances performance in cross-modal retrieval and concept steering.

NeurIPS 2026

Salvation Lies Within: Proactive Prefix Re-forming for LLM-based Tagging

SHULAN WANG, Yingjie Zhu, Yuting Yan, Ke Cheng, Yan Chen, Sheng Zhang, Hefei Guo, Qidong Zhang, Zhengyong Zhang, Yibo Jin, Zhuzhong Qian

Industrial personalized recommendation increasingly adopts LLMs for offline intent tagging (e.g., user interest from installed apps or browsing history), where each user corresponds to one prompt with thousands tokens. While shared prefix among prompts can improve the inference efficiency, the reusable part is actually dwarfed by user-specific records. We observe that even a slight $\textit{discordance}$ in preceding records prevents two prompts from sharing a longer prefix, revealing an opportunity to proactively re-form the common part from within, by adjusting the internal orders, with ensured accuracy for intent tagging. Realizing this at industrial scale is challenging: (1) the data preparation and the inference operate separately; (2) re-forming must complete within minutes for massive prompts under strict SLO; and (3) user data evolves continuously, requiring incremental updates. We present $\textit{PrefixShakeup}$, a system that enables $\textit{proactive prefix re-forming}$ before actual inference, intrinsically enlarging the common part from the source. PrefixShakeup, bridges the data and inference by enhancing the datasets during its preparation, thereby increasing the reuse. It combines three techniques: (1) a prefix model that tolerates a bounded number of records, instead of requiring strict prefix matching; (2) an alleviator that reorders both records within each prompt and the prompt positions to maximize the reuse under limited HBM, upon the kernel-based acceleration for scoring the similarity; and (3) an adaptor that supports incremental changes via lightweight management and necessary cache over time, to avoid full re-computation. We implement PrefixShakeup, on Ascend NPUs and evaluate it in the mirror environment. Compared to state-of-the-art inference, PrefixShakeup, improves throughput by up to 2.1$\times$, with controlled tagging accuracy.

NeurIPS 2026

Saliency-Aware Multi-Route Thinking: Grounding and Reasoning on Vision-Language Agents

Mingjia Shi, Yinhan He, Yaochen Zhu, Cassie Dong, Jundong Li

A vision-language (VL) agent wraps a frozen vision-language model (VLM) into a test-time system that may call external tools during execution before producing a response. The central problem is how the VLM and its tools interact across multiple steps. Two recipes are common, both rigid. Thinking for longer (borrowed from text-only agents) sharpens reasoning, but without in-loop visual refresh, it lets visual evidence decay into hallucination. Querying tools more often, as traditional agents do, treats outputs as ground truth, a rigid commitment that fails when calls are noisy. We propose Saliency-Aware Principle Selection (SAP), a training-free inference-time method that avoids both rigidities: it searches a broad space of high-level principles, short textual directives (e.g., ``re-examine the image whenever an intermediate conclusion is formed'') that each prescribe a different way for the VLM to weigh tool advice across steps, and selects the principle whose parallel reasoning routes best fit the actual visual evidence. Tool outputs are treated as advisory (consulted, never authoritative), and a population-based evolutionary loop drives the search. Under the same token budget as long chain-of-thought, SAP substantially reduces object hallucination while remaining competitive on reasoning-heavy benchmarks. Being training-free and composed of independent routes, SAP is plug-and-play on any VLM and parallel for modern agent deployment.

NeurIPS 2026

SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity

Zhenghao Gan, Yichen Bao, Yifei Liu, Chen Chen, Quan Chen, Minyi Guo

Efficient LLM inference scheduling is crucial for the user experiences. However, LLM inferences exhibit remarkable demand uncertainty (with unknown output length beforehand) and hybridity (being both compute and memory intensive). Existing LLM schedulers rely on simple heuristics or focus purely on compute resource, suffering suboptimal performance. In this work, we propose SageSched, an efficient LLM scheduler that properly handles demand uncertainty and hybridity of inference workloads. SageSched combines prompt contents with the past inference results to predict output-length distribution in a light-weight and also accurate manner. Meanwhile, it models the true service cost of an inference request with both compute and memory aspects considered. Finally, SageSched employs a uncertainty-aware scheduling policy that can yield the best overall efficiency given the request cost distributions. Testbed experiments over diverse setups confirm that SageSched can attain an efficiency improvement of over 28.7%.

NeurIPS 2026

Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails

Gert Lek, Abele Mălan, Chaoyi Zhu, Pin-Yu Chen, Robert Birke, Lydia Chen

Guard models are the last line of defense between a language model and a harmful output, yet their training objective is surprisingly narrow. Existing guards learn to predict a single verdict token from a conversational context, concentrating supervision on a single target. The consequences are structural: models latch onto shortcut features, are overconfident, and remain sensitive to where safety evidence appears in the sequence rather than its role in the full context. We propose a different framing. Rather than predicting a label from text, our $\textbf{LLaDA Guard}$ asks which label better explains the text: scoring the prompt or response under each label hypothesis and classifying based on their difference. This shifts supervision to every token in the moderated region, forcing the model to account for full content rather than its most discriminative fragments. We instantiate this idea with a masked diffusion language model, fine-tuning LLaDA-8B-Instruct with a class-conditional reconstruction objective using LoRA and requiring no architectural changes beyond the base model. LLaDA Guard leads on average rank against discriminative baselines trained on stronger backbones across seven held-out safety benchmarks, while exhibiting substantially better confidence calibration (ECE 0.0875 vs. 0.1384 for Qwen3Guard), less over-defense on benign prompts with $\texttt{unsafe}$-looking cues, and less prompt leakage when moderating responses. Its generative nature further enables token-level risk localization as a natural byproduct, yielding a pipeline for rewriting $\texttt{unsafe}$ prompts into $\texttt{safe}$ equivalents without additional training and achieving a 60.7% average conversion-to-$\texttt{safe}$ rate. The weights and code for reproduction are available at the following [anonymized repository](https://anonymous.4open.science/r/LLaDA-Guard2026-B056/).

Keep browsing

More papers from top AI conferences

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