NeurIPS 2026 Papers

We present $\textbf{ROCKET}$, a training-free model compression method that achieves state-of-the-art performance in comparison with factorization, structured-sparsification and dynamic compression baselines. Operating under a global compression budget, ROCKET comprises two key innovations: First, it formulates layer-wise compression allocation as a multi-choice knapsack problem, selecting the optimal compression level for each layer to minimize total reconstruction error while adhering to a target model size. Second, it introduces a single-step sparse matrix factorization inspired by dictionary learning: using only a small calibration set, it sparsifies weight coefficients based on activation-weights sensitivity and then updates the dictionary in closed form via least squares bypassing iterative optimization, sparse coding, or backpropagation entirely. $\textbf{ROCKET}$ consistently outperforms existing compression approaches across different model architectures at 20–50\% compression rates. Notably, it retains over 90\% of the original model’s performance at 30\% compression without any fine-tuning. We will release the code implementing ROCKET upon paper acceptance.

Driver monitoring concerns determining not only what a driver is doing, but whether the behavior violates a driver-behavior safety rule under the current driving context. Existing distracted-driving benchmarks largely reduce this problem to closed-set action recognition, often missing cases where the same behavior changes meaning with road scene, vehicle state, duration, and rule-specific exceptions. We present **ROAD**, a rule-grounded context-aware open-world framework for driver anomaly detection. ROAD represents driver-monitoring constraints as structured rule cards and jointly reasons over in-cabin driver evidence, road-context video, optional vehicle-state metadata, and open-world semantic cues to produce structured anomaly judgments: driver action, violated rule, anomaly score, supporting evidence, exception status, and explanation. Unlike generic MLLM prompting, ROAD separates perception, rule grounding, and semantic generalization. Road context modulates driver-centric evidence, rule-card encodings select rule-relevant evidence, and a LoRA-adapted MLLM extracts open-vocabulary safety cues from compressed video evidence. This design targets two forms of open-world generalization: recognizing unseen driver behaviors beyond a fixed action taxonomy and adapting to new or revised rule cards. We further introduce ROAD-Bench, a rule-grounded benchmark with context, exception, evidence, anomaly-score, and explanation annotations. With a three-stage curriculum from action primitives to context-rule alignment and anomaly adaptation, ROAD outperforms evaluated baselines across driver-distraction recognition, open-world behavior recognition, and rule-grounded anomaly detection, using an 8B multimodal backbone. It achieves 92.01\% average accuracy over seven driver-recognition benchmarks, 77.9\% AUROC and 46.9\% unseen-class F1 in behavior recognition, and 73.6\% AUROC, 68.3\% rule accuracy, and 54.5\% Expl.-Rule F1 on ROAD-Bench.

Online reinforcement learning (RL) has achieved significant success in decision-making tasks, but modern online RL remains highly sensitive to the quality of training experience. Understanding the role of training data in online RL is challenging because the training distribution evolves together with the policy, causing the influence of the training data to propagate across future optimization and future data collection. Existing data-attribution methods for online RL primarily focus on local influence within a single training round, overlooking the non-local data influence across multiple training rounds. In this work, we formalize data attribution in online RL through a trajectory-level leave-one-out quantity, RL-LOO, which measures how one training sample influences a downstream target after subsequent online updates have taken place. We then derive RL-Inf, a first-order estimator that propagates data influence through both optimization effects and policy-induced sampling effects, and provide theoretical guarantees on its approximation accuracy under smoothness assumptions. Our analysis further disentangles these two effects and shows both theoretically and empirically that the full RL-Inf estimator can often be well approximated using the optimization effect alone. Building on this observation, we develop RINSE, a practical data filtering method for online RL. Experiments on standard control benchmarks and an RLHF-style toxicity-mitigation setting show that RINSE improves training efficiency and final performance over standard PPO and local attribution baselines. These results suggest that RL-Inf provides a practical and principled framework for understanding and improving online RL.

Time-aware retrieval is crucial for long-horizon LLM agents to effectively leverage ever-growing long-term memory. Existing methods focus on lexical or semantic similarity, leading to target memories being crowded out by temporally mismatched yet semantically similar candidates. Even time-aware approaches inject temporal cues only during memory organization or answer generation, overlooking temporal constraints at the retrieval stage, where candidate selection occurs—the root cause of the displacement. Inspired by the temporal contiguity effect in human episodic memory, we propose TIDER (Temporal Interval-driven Dual-channel Evidence Retrieval), a time-aware agentic retrieval framework. Central to TIDER is a reinforcement learning (RL)-trained temporal interval locator that infers the temporal windows in which the evidence lies. RL optimizes window localization as a discrete, non-differentiable retrieval decision, using composite rewards to convert sparse answer supervision into fine-grained retrieval feedback. These temporal windows first define the temporal retrieval channel; the retrieved candidates are then merged with results from the semantic channel and reranked by proximity to the windows. This temporal grounding enables TIDER to retrieve temporally aligned evidence that would otherwise be drowned out by the volume of semantically similar yet temporally mismatched memories. With a lightweight 1.7B locator, TIDER achieves state-of-the-art accuracy on both long-horizon memory benchmarks—61.52% on LifeBench (+8.82%) and 78.96% on LoCoMo (+3.66%), which indicates that temporal cues are crucial for pinpointing target evidence amid a vast pool of semantically similar historical events in long-term daily-life memory.

Verifying that two quantum circuits are equivalent is a critical challenge in compiler validation. A common approach is to transform the circuits into a tensor network and then iteratively contract tensors in the network. The order in which contractions are applied has a crucial influence on the complexity, as tensor size may grow exponentially in the number of qubits. This motivated research into heuristic policies to find good contraction orders, including recent work based on reinforcement learning (RL). Orthogonally, to mitigate the complexity of an explicit tensor representation, tensor decision diagrams (TDDs) have been proposed as a compact symbolic representation. However, also the TDD performance is sensitive to the contraction order, and policies designed for tensor networks do not perform well in case of a TDD representation. In this paper, we propose an RL framework to obtain a graph-neural-network policy that navigates the trade-off between arithmetic complexity and TDD size. Experimental results demonstrate that a policy learned with our framework is effective at taming the symbolic representation size.

The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and supervised fine-tuning (SFT). We question this status quo by training a LLM from scratch and applying RL, SFT, and SFT followed by RL directly to intermediate pre-training checkpoints. We find that RL is effective very early, and often matches the full SFT$\to$RL pipeline early as well. Through experiments on harder problems, we find that targeted pre-training data composition is a strong lever for RL effectiveness, even more so than model scale. Beyond reasoning accuracy, applying RL directly to base checkpoints expands the model's distribution; the sharpening effect reported in recent work arises only when RL follows SFT. The general capabilities of the model remain essentially unchanged by RL, while they degrade following SFT. Finally, we merge RL and SFT objectives by \textit{parallel averaging}, which outperforms across all other training methods discussed, across metrics, while preserving general capabilities. Together, these results suggest that LLM training might benefit from an expanded use of RL.

Large language models are increasingly deployed as long-lived agents that must adapt across users, tasks, domains, modalities, and feedback regimes without access to model weights. Existing black-box adaptation methods typically optimize a single prompt, maintain an undifferentiated memory, or rely on repeated rollout-heavy search. However, these designs struggle when streams of input are nonstationary, feedback is sparse, and failures from one task family can contaminate behavior on another. We introduce RIZZ (**R**outing **I**nteractions to Near **Z**ero-interference **Z**ones), a continual adaptation framework for compound language-model systems that learns entirely through verifier-gated memory, routing, and prompt compilation. RIZZ organizes input streams into dynamically spawned memory branches. At inference time, either while online or offline, a context-aware router selects or creates a branch that retrieves branch-local, global, graph-structured, and working-memory context, which is compiled into a bounded prompt together with retrieved task evidence. After the model acts, task verifiers score the output, and only verified interactions can update memory, promote reusable rules, demote harmful rules, or create anti-patterns. This yields a black-box agent that improves through persistent natural-language feedback while explicitly controlling interference. RIZZ targets the regime where adaptation must occur online under context budgets. Finally, we demonstrate the effectiveness of our framework against state-of-the-art baselines on competitive benchmarks.

Interactive regex search over large text columns needs exact matches under low latency, but indexes help only when a pattern exposes selective fragments. For LIMIT-k queries, the immediate bottleneck is choosing a few indexable keys that reach match-rich candidate buckets before regex verification. RIVET casts this step as constrained regex-to-key generation: a column-specific translator emits short keys, an existing index retrieves candidates, and the native regex engine verifies every output record. Training from repeated regex-key hits moves probability mass toward effective keys, so finite online sampling spends fewer regex checks before collecting the requested matches. Across four large datasets, RIVET reaches 35.8 ms median latency, improves over the strongest baseline REI by 3.4–36×, and reaches up to 1773× speedup over sequential scan. The same mechanism improves TPC-H query plans, preview retrieval under latency budgets, and 80 human-authored OOD regex queries, showing that regex-to-key generation translates into end-to-end system gains.

On modern production text-to-image systems, successful policy violations are rare, and previously effective human-written seeds are often patched out. Current automated red-teamers are poorly matched to this regime in two ways: unreliable success measurement and poor exploration. First, we find that judges widely used in prior T2I red-teaming work are unreliable under vague unsafe-content targets: they either miss true violations or reward benign borderline images on hardened APIs. We therefore define strict category-specific success criteria and calibrate strong VLM judges against human labels. Second, we show that broadly used prompt-modification pipelines do not solve the exploration problem: on harder guardrail settings they remain tied to seed prompts, fail to transfer, or cannot bootstrap positive examples. We introduce RISE, which evolves reusable strategies used to generate prompts rather than rewriting them one by one. The best discovered strategies are then reused to generate attacks across new scenarios. On DALL·E 3, Nano Banana 2 (Google) and GPT-Image-2, RISE reaches up to 13\% human-verified ASR; under the same calibrated evaluation, prior methods with reported ASR as high as roughly 30\% fall to near zero.

Millimeter-wave radar is promising for privacy-preserving human sensing, yet current radar-to-language pipelines typically map sparse point clouds into either global clip features or discrete token codes that are only weakly matched to the structure expected by large language models (LLMs). We present RILA, a radar-native structured interface layer for large-language-model adaptation, which converts sparse mmWave radar point clouds into LLM-readable event-aware tokens. RILA combines kinematic phase-space tokenization, flow-aware dual-order serialization, dual-scan selective state-space encoding, and an event-aware token abstraction that exposes both global clip context and temporally localized motion units to the language model. The same interface supports three language tasks through a shared decoder: clip summary generation, ordered event description, and temporal question answering. To stabilize the interface before instruction tuning, we introduce a structured interface-language alignment objective over clip and event tokens. We evaluate RILA using physics-aware synthetic pretraining and real-world mmWave adaptation under controlled radar-native baselines and matched decoder settings. This formulation reframes radar-to-LLM modeling as an interface design problem and studies how radar-native structure, rather than only generic cross-modal projection, determines whether sparse mmWave point clouds can be effectively understood by LLMs.

LLM-based multi-agent systems (MAS) improve complex reasoning through collaborative decomposition, verification, and synthesis, but their performance can degrade sharply when compromised agents inject misleading intermediate messages. Existing topology methods rely on fixed communication patterns or query-adaptive graphs, but rarely infer or intervene runtime reliability risk, leaving them fragile when compromised agents vary across queries. We study stochastic adversarial topology adaptation, where compromised agents shift across graph positions and rare cascades dominate the high-loss tail. To address this setting, we propose RIGOR, a topology-adaptation framework that couples runtime risk inference with tail-aware training. RIGOR combines Risk-Gated Topology Construction (R-GTC), which probes agent behavior, estimates per-agent risk, and edits the graph through soft quarantine and edge masking, with CVaR-Guided Robust Optimization (C-GRO), which trains the editor on high-loss episodes rather than average gain alone. Across six benchmarks and two backbones, RIGOR consistently outperforms existing MAS baselines under query-varying misleading-message attacks, achieving an average 21.09\% accuracy improvement over the strongest baseline on Qwen3.5-35B-A3B. Tail-subset and position-wise analyses further show that these gains stem from improved robustness against worst-case cascades and dynamically changing compromised-agent positions. The code is available for anonymous access at https://anonymous.4open.science/r/RIGOR-0D7D.

Capturing screens is common, but photos of emissive displays are often influenced by \emph{flicker-banding} (FB), some alternating bright--dark stripes due to temporal aliasing between a camera's rolling-shutter readout and display's brightness modulation. Unlike moir\'e degradation, FB remains underexplored despite its frequent and severe impact on readability and perceived quality. We formulate FB removal as a dedicated restoration task and introduce Removal of Image Flicker-B}anding via Latent Diffusion Enhancement, RIFLE, a diffusion-based framework designed to remove FB with fine details. We propose Banding-Suppressed High-Frequency Prior (BSHP), which combines gradient-based high-frequency localization with a smooth structural support map to build a compact restoration prior, and injects it into the restoration backbone via multi-stage FiLM modulation. Moreover, Masked Loss (ML) is proposed to concentrate supervision on banded regions without sacrificing global fidelity. To overcome data scarcity, we provide a simulation pipeline synthesizing FB in the luminance domain with stochastic jitter in banding angle, spacing, and width. Feathered boundaries and sensor noise are also applied for a more realistic simulation. For evaluation, we collect a paired real-world FB dataset with pixel-aligned banding-free references captured via long exposure. Across quantitative metrics and visual comparisons on our real-world dataset, RIFLE consistently outperforms recent image reconstruction baselines. To the best of our knowledge, it is the first work to research the simulation and removal of FB. Our dataset and code will be released soon.

Retrieval is increasingly moving from one-shot matching toward interactive reasoning, where language agents iteratively inspect evidence, reformulate queries, and search again. Training such agents raises a credit-assignment challenge: executable actions such as queries or summaries can be directly evaluated by the retriever, while latent reasoning steps are not directly observable and only affect future executable actions. This asymmetry makes outcome-level reward assignment unreliable, as the same final reward may credit reasoning steps that did not actually shape retrieval success. We propose RICE-PO, a critic-free policy optimization framework that converts retrieval interactions into localized learning signals. RICE-PO selects high-uncertainty executable actions as anchors, evaluates local counterfactual branches using retrieval metrics, and propagates credit to latent reasoning steps only when reasoning-to-action influence is strong and future residual effects are stable. On BRIGHT and BEIR, RICE-PO consistently outperforms prompt-based agents and group-based RL baselines under the same retriever setting. These results show that the structure of agent-environment interaction itself can provide useful supervision for training reasoning-based retrieval.

The Maximal Independent Set (MIS), Dominating Set (DS), and Vertex Cover (VC) problems are fundamental combinatorial optimization problems with wide-ranging applications. We identify a key property of these problems: by finding a cut in the graph and determining the states of vertices associated with the cut, the graph can be decomposed into multiple subgraphs whose solutions are independent of each other. Therefore, we classify MIS, DS, and VC as Edge-Cut Separable Problems (ECSPs). This property enables a natural divide-and-conquer strategy, which significantly reduces the computational complexity and allows neural networks to scale to large-scale graphs that were previously intractable. Based on this property, we propose a recursive framework that leverages this property to approximately solve ECSPs, namely \ours. Our framework consists of two major components: a partitioner that identifies a cut in the graph, and a predictor that solves the cut-determination sub-problem (CDSP) to determine the states of vertices associated with the cut. By recursively applying these components, RGF generates a complete solution for the original ECSP instance. Additionally, through partial prediction, the memory consumption is significantly reduced, enabling RGF to handle real-world large graphs. Experimental results validate the advantages of RGF: the performance of our method is up to 2.13\% better than the state-of-the-art machine learning (ML)-based approach, and our approach can handle real-world large graphs with up to 11M vertices.

Image geo-localization aims to determine where a photograph was taken, a task that often requires more than recognizing visible landmarks. Human experts typically solve it through an iterative workflow: they inspect informative regions, form location hypotheses, seek external evidence, and revise their judgments as new clues appear. Existing methods only partially capture this process: direct prediction methods bypass evidence acquisition altogether, while retrieval-augmented methods introduce external evidence but usually provide limited supervision on the intermediate decisions of where to search, how to query, and how to filter noisy results. We present REVERSE, a framework that reinforces the interplay between evidence search and verification to enable multi-turn agentic reasoning. REVERSE teaches three intermediate decisions: where to look, what to query, and what evidence to trust. To support this, we construct tool-grounded trajectories with annotated region selections, search observations, and geo-informative evidence labels, and introduce process rewards for visual grounding, query utility, and evidence discrimination. An offline search cache makes retrieval observations stable and reusable during reinforcement learning, enabling dense supervision over noisy search results. With a 4B model, REVERSE outperforms strong retrieval-augmented baselines and rivals substantially larger models on Im2GPS3k and YFCC4k.

Robust 3D lane detection requires accurate metric road geometry recovery from visual inputs, yet conventional RGB-based approaches suffer from fragile lane evidence under adverse illumination, motion blur, and long-range perspective compression. Event cameras offer complementary high-temporal-resolution, high-dynamic-range structural cues that are robust to these challenges, but their sparse, motion-dependent responses cannot be directly fused into consistent 3D geometry. In this paper, we present the first attempt to introduce event cameras into 3D lane detection. To enable systematic research, we first build two multimodal benchmarks with metric 3D lane annotations: DSEC-3DLD (real-world sequences) and Ev-OpenLane (large-scale simulated sequences). We further propose RETR, a structure preserving transformer that converts complementary RGB and event observations into coherent 3D lane geometry. RETR first aligns modality consistent evidence through Reciprocal Context Flow Fusion, then preserves thin and uncertain lane structures with Uncertainty Aware Structural Consolidation, and finally decodes ordered lane hypotheses using a Geometry State Decoder with proposal conditioned initialization, reference conditioned query evolution, and diversified geometric inquiry. Extensive experiments show that RETR achieves state-of-the-art performance on both benchmarks, especially showing strong improvements in challenging lighting and complex road geometry scenarios.

Accurate short-term forecasting of residential energy load and indoor temperature is essential for home energy management systems, grid-level demand response participation, and community-level energy efficiency programs. Domain adaptation methods and transfer learning have shown promise in improving forecasting accuracy under data heterogeneity and scarcity scenarios commonly observed at the residential level. However, progress remains limited by the absence of comprehensive residential datasets: existing ones are narrow in target coverage and lack structured support for cross-domain evaluation. To address this, we introduce RESCAST-100K, a large-scale residential forecasting benchmark for studying cross-domain generalization. It exposes a configuration-driven interface that instantiates source and target domains along interpretable axes, such as geography, climate zone, wall construction, and heating equipment, supporting systematic evaluation of transfer learning, domain adaptation, and zero-shot generalization under controlled domain shifts. The benchmark covers approximately 100,000 EnergyPlus-simulated U.S. homes derived from ResStock, providing 15-minute time series of three coupled targets per home, namely total load, HVAC (heating, ventilation, and air conditioning) load, and indoor temperature, together with weather channels, HVAC setpoints, and over 40 static building covariates. Finally, it integrates five real-world residential datasets under a unified schema, supporting sim-to-real evaluation on the same tasks. We benchmark models from recurrent, attention, and MLP-mixer architectures for zero-shot performance across different domains, under missing input data conditions, for each task. Cross-attention and MLP-mixer based models consistently outperform recurrent and classical transformer-based baselines under domain shift. RESCAST-100K is intended to support the machine learning and building analytics communities in advancing cross-domain residential forecasting at the home, community, and grid levels.

Bird's-eye-view (BEV) perception has emerged as a cornerstone of autonomous driving systems, providing a structured, ego-centric representation critical for downstream planning and control. However, real-world deployment faces challenges from sensor degradation and adversarial attacks, which can cause severe perceptual anomalies and ultimately compromise the safety of autonomous driving systems. To address this, we propose a resilient and plug-and-play BEV perception method (RESBev), which can be easily applied to existing BEV perception methods to enhance their robustness to diverse disturbances. Specifically, we reframe perception robustness as a latent semantic prediction problem. A latent dynamic predictor is constructed to extract spatiotemporal correlations across sequential BEV observations, thereby learning the underlying BEV state transitions to predict clean BEV features for reconstructing corrupted observations. The proposed framework operates at the semantic feature level of the BEV perception pipeline, enabling recovery that generalizes across both natural disturbances and adversarial attacks without modifying the underlying backbone. Extensive nuScenes experiments show RESBev notably enhances BEV perception robustness against natural disturbances and adversarial attacks, with latency, parameter and memory analyses verifying its excellent robustness-efficiency trade-off.

Parkinson's disease and other gait-related neurological disorders manifest in subtle but biomechanically meaningful changes in how patients move, making computational gait phenotyping a valuable tool for clinical assessment. Yet existing latent representations of motion are typically learned from data alone and miss the biomechanical structure that gives clinical motion its diagnostic meaning, leaving them vulnerable when training cohorts are small or acquisition sites differ. We propose REINS (Riemannian Embedding for INertia-induced motion Spaces), an Euler-Lagrange-induced motion representation that uses the generalized inertia matrix of articulated systems to define a biomechanically grounded geometry on configuration space. Because kinetic energy is itself a quadratic form in velocity weighted by the inertia matrix, this metric is a mechanically determined Riemannian structure, and we learn a latent embedding of the resulting structured space. By defining the representation space itself through rigid-body dynamics rather than enforcing physics as a post-hoc penalty, REINS aligns the geometry of motion representation with the same physical laws clinicians rely on to interpret gait. We apply the framework on Parkinson's disease gait analysis, where deviation from healthy motion is measured as a geodesic distance under the inertia-induced metric, and report results on healthy-control vs.\ PD discrimination and UPDRS-gait severity correlation.