NeurIPS 2026 Papers

Differentiable signal parameterizations such as implicit neural representations (INRs) and hybrid models are increasingly central to computational imaging, yet principled tools for evaluating reconstruction fidelity at finite model size remain limited when ground truth is unavailable. We introduce a framework for predicting the reconstruction error of compressive signal parameterizations, yielding non-asymptotic, signal-specific bounds that are both theoretically sound and efficiently computable without access to the ground truth signal. Specifically, we prove that when parameterization-based compression satisfies certain natural properties, the compression error at any compression level is bounded by a simple scaled difference between model predictions at different compression levels. We verify these properties for representative model families including interpolated grids, Fourier feature networks, multi-resolution hash tables, and tensor factorizations, and show empirically that the resulting worst-case guarantees can be efficiently adapted into signal-specific error predictors that are tight and generalizable. Across direct fitting of synthetic and natural signals, and inverse problems including radiance field and MRI reconstruction, our method closely tracks global error curves and yields informative local error heatmaps without ground-truth access.

Large language model (LLM) agents often keep the needed value in their prompt and still fail to pass it to a later tool call. We study this failure at the level of \textit{field routing}: an earlier observation may expose an \texttt{order\_id}, policy flag, or nested item, and a later call must bind that field to the right argument. We formalize tool use as a boundary-indexed field-routing graph and introduce Information Utilization Rate (IUR), which measures whether each required dependency edge is realized in the later tool call. A 400-dependency expert audit, task-success correlations, and discriminant checks validate IUR as a field-use signal. On a 357-task public evaluation from ToolSandbox \texttt{STATE\_DEPENDENCY} (192 named scenario variants) and the original-repository $\tau$-bench retail/airline files (115+50 tasks), aggregate dependency-level IUR across GPT-4o, Claude-3.5-Sonnet, Llama-3.1-70B, and Qwen-2.5-72B falls from 451/548 (82.3\%) at boundary distance $\delta=1$ to 144/283 (50.9\%) at $\delta=5$, a 31.4-point drop, with mean context length only 3,094 tokens. Token-matched analyses and boundary transformations show that raw token length and lost-in-the-middle do not explain the curve by themselves. The same field-level view also leads to a compact intervention. Boundary-Aware Field Memory (BAFM) predicts live fields without gold dependencies at inference time and injects field reminders rather than whole observations. In paired GPT-4o runs, BAFM improves task success from 144/357 (40.3\%) to 192/357 (53.8\%), a 13.4-point gain over the base agent and 2.8 points over self-predicted retrieval-augmented generation. The results recast long-chain tool use as state propagation over fields: the central question is which prior values remain live for the next action.

Low-label transfer is often decided by a practical question: after a representation looks useful, how many labels are still needed to learn the downstream boundary? Existing transferability and probe-quality scores rank global alignment, likelihood, margins, or calibration, but they do not measure how much target data remains close to the fitted decision boundary, where scarce labels are most costly. We propose **effective boundary complexity**, a label-budget diagnostic for frozen representations and linear probes. It measures mass in a thin strip around the learned boundary and normalizes it by class balance, so dense ambiguous regions and rare-class difficulty are both counted. We prove that, under a smooth representation map, this boundary mass does not change because of generic volume expansion: density change and tangential surface change cancel at first order, leaving only stretch or compression in the boundary-normal direction. This yields a cached-feature estimator that fits a probe on one split, counts held-out features near its boundary, and avoids high-dimensional density estimation. Experiments support the diagnostic at three levels. Controlled transformations match the predicted law across 74 maps with 0.38% median relative error. On real frozen features, normal-direction changes move both measured boundary mass and label demand, while tangent changes do not. A differentiable surrogate reduces measured complexity by 16–36% at matched top-1 utility. Finally, CIFAR-100 and Tiny-ImageNet audits show boundary mass acting as a second-stage diagnostic for near-tied representations, with external multiclass results showing how label-grid saturation limits policy-level gains on label grids where many tasks tie.

Progressive image compression reconstructs images from prefixes of a single bitstream and therefore involves sequential latent inference under partial observations. Existing trit-plane codecs mainly treat decoded trits as discrete symbols for probability prediction, without fully exploiting their role as interval constraints on the underlying continuous latents. We propose bound-conditioned latent inference (BLI), a framework that reformulates progressive trit-plane coding as sequential latent inference under shrinking interval constraints. At each coding step, the trits decoded so far define lower and upper bounds for each latent element. BLI uses the center and width of these bounds, together with hyperprior information shared by the encoder and decoder, to jointly refine the Gaussian parameters $(\mu,\sigma)$ for entropy modeling and the latent estimate $\hat{y}$ for reconstruction. As additional trits are decoded, the feasible intervals shrink monotonically, yielding tighter constraints for the next inference step and enabling flexible in-plane refinement schedules. Experiments on Kodak, CLIC, and JPEG-AI show that BLI achieves state-of-the-art rate-distortion performance among progressive image codecs, reducing BD-rate by $17.80\%$ over DPICT and by $7.98\%$ over CTC on Kodak, while replacing CTC's plane-specific predictors with a shared model that uses about $5.3\times$ fewer parameters and achieves lower latency than CTC.

Recent years have witnessed meteoric progress in *reasoning models*: neural networks that generate intermediate *reasoning traces* (RTs) before producing a final output. Despite the rapid advancement, our understanding of how RTs support reasoning, and where this paradigm fails, remain incomplete. To promote greater clarity, we introduce PITA: a novel large-scale dataset of over 23 million statements in propositional logic and their corresponding proofs. As a benchmark for robust reasoning, we focus on length generalization: if a model is trained to determine truth or falsity on statements with proofs up to fixed length, how well does it generalize to statements requiring longer proofs? We propose notions of (1) *task depth* and (2) *task breadth*, which measure respectively (1) the number of proof steps required to solve a proposition and (2) the number of unique propositions within a task family. We vary these quantities across subsets of PITA, and find that RT models generalize well on relatively *broad* and *shallow* subsets, while deteriorating on relatively *narrow* and *deep* subsets compared to non-RT baselines. As a controlled point of comparison, we study a separate, tractable transitive inference task that exhibits qualitatively similar behavior. Our accompanying theory explains the scalings observed in this simpler setting, suggesting one mechanism by which breadth can favor RT models while depth can expose long-context weaknesses. Our findings suggest salient benefits and limitations of proof-like reasoning traces in controlled length-generalization settings.

One key application of autoencoders is to learn how to compress token sequences. Since the difficulty of compression depends on factors such as sequence length, vocabulary size, structural regularity, and input noise, it would be valuable to understand how these factors affect the performance of different architectures. Surprisingly, however, there is no benchmark for comparing autoencoder architectures that allows control over these aspects of difficulty. We introduce the Bottleneck Benchmark (BB), an open experiment framework in which encoder and decoder communicate only through a fixed-size latent and that allows to configure the previously mentioned difficulty aspects for any customizable data generator. As a case study, we evaluate BiLSTM, Transformer, and Bidirectional SSM encoders on copy, sort, and set tasks, finding that performance differences arise from inductive biases under noise and length rather than raw capacity.

The increasing prevalence of preference-based learning, particularly for machine learning models interacting with human users, gives rise to scenarios where the model's decision should cater to the preferences of a number of users. Due to the inherent misalignments in such preferences, it is natural to seek a fair decision-making paradigm. Motivated by that, we pose the problem of fair multi-user dueling bandit, where each user's preferences over pairs of actions are encoded by a preference matrix unknown to the agent. We design a Nash social welfare objective based on the Borda scores of the individual user preferences. The notion of the Borda score measures the average likelihood of an action being preferred over the other actions, and importantly, it does not require the existence of a completely dominant action. Considering online learning in this general setting, we construct hard instances and establish a minimax lower bound on the achievable regret. We also design an explore-then-commit algorithm and derive an upper bound on its worst-case regret. Furthermore, we formulate a fair multi-user generalized linear dueling bandit to enable modeling large action spaces, which typically necessitate a structured representation. In this setting, too, we establish a lower bound on regret and an upper bound on regret for a proposed explore-then-commit algorithm.

Diffusion policies have achieved strong performance in reinforcement learning (RL) due to the exceptional expressivity in capturing complex action distributions. However, existing approaches focus primarily on positive samples and lack explicit modeling of negative samples, thereby failing to fully exploit this representation capacity and ultimately limiting performance. To mitigate this problem, we propose BOBAC (BOotstrapped Bipartite Actor-Critic), a novel method for diffusion policy optimization via pairwise preference learning. Bridging the gap between distribution modeling and preference learning, we reformulate diffusion policy optimization within a preference-aware framework via the Bradley-Terry (BT) modeling, which enables the effective exploitation of negative samples through relative ranking. Since the original BT loss assigns the same weight to all pairs regardless of their varying importances, we further design a soft-gate mechanism to adaptively weight each pair according to its Q-gap. Experimental results on 6 MuJoCo tasks and 4 H1Bench tasks demonstrate that, compared with representative model-free and generative-policy RL baselines, BOBAC achieves state-of-the-art performance with consistent improvements in all continuous-control environments.

Code agents are rapidly lowering the barrier for developers to work with unfamiliar repositories, and are increasingly adopted for tasks such as building prototypes, reproducing experiments, and adding features. Reliably executing these tasks depends on a critical prerequisite: the target repository must first be successfully set up and brought into a usable development state. This bootstrapping process requires substantial trial-and-error exploration by code agents, yet the resulting knowledge (e.g., resolved dependencies, repair strategies) remains trapped in a single conversation, unavailable to future agents or developers. We therefore formulate repository bootstrapping as a reusable startup knowledge problem and introduce BootstrapAgent, a multi-agent framework that distills bootstrap exploration into a persistent, verifiable, agent-consumable .bootstrap contract. Through CI evidence extraction, structured planning, deterministic Docker-based verification, and trace-driven repair, BootstrapAgent generates a contract covering environment setup, diagnostic checks, minimal verification, and accumulated repair knowledge. We further propose warm repair with clean replay to accelerate iterative debugging without sacrificing cold-start reproducibility, and a two-level verification strategy to prevent reward hacking. Experiments on three benchmarks show that BootstrapAgent achieves a 92.9% success rate, outperforming the baseline by over 10% while reducing downstream agent token usage by 25.9% and build time by 22.3%.

Text-to-image diffusion models can synthesize high-quality images, yet the outcome is notoriously sensitive to the random seed: different initial seeds often yield large variations in image quality and prompt–image alignment. We revisit this “seed effect” and show that attention dynamics over prompt core tokens, the content-bearing words, measured during the first few denoising steps, strongly predict final generation quality. Building on this observation, we introduce Attention-Based Seed Selection (ABSS), a training-free, plug-and-play method that ranks seeds for a given prompt by leveraging cross-attention to core tokens during the denoising process. ABSS requires no finetuning and does not alter the initial noise; it scores and ranks all candidate seeds, keeps only the top-k for full generation, and discards the rest, without relying on a fixed accept/reject threshold. Operating purely at inference time, ABSS can serve as a lightweight pre-selection add-on for existing seed-optimization pipelines, enabling additional gains. Across three benchmarks, extensive experiments show that ABSS enables consistent improvements in text–image alignment and visual quality for Stable Diffusion variants, as corroborated by human preference and alignment metrics.

Reinforcement Learning with Verifiable Rewards (RLVR) has become an important approach for improving the reasoning capabilities of large language models (LLMs). On-policy training remains the dominant RLVR paradigm, but its reliance on fresh rollouts leads to poor data efficiency. To address this bottleneck, off-policy paradigm has attracted increasing attention by reusing historical trajectories through replay buffers. Despite its efficiency advantages, off-policy training often struggles to match the performance of on-policy training. Our analysis reveals that this limitation primarily stems from data staleness introduced by replay buffers: to maintain training stability, mainstream algorithms discard a large fraction of high-staleness optimization signals, leading to substantial performance degradation. To address this issue, we propose **STAR** (**St**aleness-**A**ware **R**eplay), a data-centric replay framework decoupled from specific optimization algorithms. STAR improves off-policy RLVR by constructing low-staleness and high-quality training data. Experiments on a range of mathematical reasoning and code generation tasks show that STAR consistently improves off-policy RLVR with up to 19% relative performance gains, and enables it to surpass the on-policy baseline using only around 13% of the rollout data while achieving 5x-6x wall-clock speedup.

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for enhancing reasoning in Large Language Models (LLMs). However, existing reward formulations typically treat exploration and consolidation as a monolithic process, resulting in entangled stage-wise learning dynamics. This contradicts the natural learning behavior of human learners. In human learning, individuals adopt distinct behavioral patterns toward mastered versus unfamiliar problems. When confronting unmastered challenges, humans prioritize broad exploration to seek viable solutions. By contrast, for well-mastered problems, they focus instead on reasoning condensation and knowledge abstraction to distill concise underlying principles. Motivated by this gap, we introduce T2T(Thickening-to-Thinning), a dynamic reward framework inspired by human learning processes. Specifically, it implements a dual-phase mechanism: (1) On incorrect attempts, T2T incentivizes "thickening" to broaden the search space and explore novel solution paths; (2) Upon achieving correctness, it shifts to "thinning", imposing length penalties to discourage redundancy, thereby fostering model confidence and crystallizing reasoning capabilities. Extensive experiments on mathematical benchmarks (MATH-500, AIME, AMC) across 5 mainstream LLMs demonstrate that T2T significantly outperforms standard GRPO and recent baselines, achieving superior performance.

Recent work on recursive architectures has shown that tiny neural networks can be surprisingly powerful on structured reasoning tasks. The trick is to model reasoning trajectories with a latent dynamical system. We argue that the inference-time behaviour of these architectures is best understood as approximate inference over latent reasoning trajectories, with deterministic recursion as the one-particle, zero-noise limit. We make this view operational through guided stochastic exploration: stochastic perturbations of the reasoning dynamics propose neighbouring trajectories, and the model's existing early-stopping head reweights them online. The framework yields three label-free diagnostics: local stability, guide alignment, and cloud-token entropy. These predict, from inference traces alone, whether the procedure will help and which of its outputs to trust. On Sudoku-Extreme it lifts exact-solve accuracy from $85.9\%$ to $98.0\%$ without retraining; on Maze-Hard the diagnostics flag a misaligned guide, as validation performance later confirms. The same machinery thus characterises both when recursive reasoning has room to improve at the trajectory level and when the model's internal guide can recover it.

Graph contrastive learning constructs augmented views and aligns corresponding instances across views to learn view-invariant representations. However, existing methods usually enforce cross-view consistency within a single representation space, lacking an explicit characterization of view-specific information. This may suppress task-relevant complementary information, reduce embedding diversity, and induce dimensional collapse. To this end, we propose Manifold-Guided Representation Disentanglement (MGRD), a plug-and-play framework for boosting graph contrastive learning. MGRD decomposes graph representations into shared and complementary subspaces. The shared subspace captures view-invariant semantics while preserving local graph structure through a graph-anchored manifold prior, whereas the complementary subspace captures residual view-specific information beyond the shared representation and is regularized by asymmetric consistency and subspace decorrelation. By jointly exploiting shared and complementary representations, MGRD balances cross-view invariance and representation diversity. Experiments on node-level and graph-level benchmarks show that MGRD consistently improves multiple GCL backbones, while theoretical and empirical analyses demonstrate its effectiveness in mitigating dimensional collapse.

Brain decoding is limited by the availability of labeled neural data, and remains challenging in low-data regimes. To address this issue, we investigate whether and when brain decoding can be boosted by augmenting small fMRI datasets with synthetic data generated by a pretrained model of fMRI responses to stimuli. We use TRIBE v2, a large encoding model pretrained on more than 1000\,hours of fMRI responses to video, audio and language. For each dataset, we evaluate systematic grids that show how the performance of image decoders varies with the amount of synthetic data used for training. Our results, based on two datasets (the 7T fMRI Natural Scenes Dataset and 3T fMRI BOLD5000), show up to 68\% improvement in Top-10 image-retrieval accuracy compared to decoders trained only on real data. Importantly, the proportion of augmented data required to reach a given image decoding performance needs to be adjusted depending on the data source. Surprisingly, image decoders trained exclusively on synthetic fMRI perform above chance in some settings, suggesting that TRIBE v2 can support zero-shot fMRI-to-image decoding. Together, these results show how large-scale models of the fMRI responses to sight, sound and language may provide a foundation to improve the data efficiency for image decoding.

Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models (LLMs). However, existing RLVR methods often suffer from exploration inefficiency due to mismatches between problem difficulty and model capability: overly difficult problems hinder reasoning path discovery, while overly simple problems offer little learning signal. To address this, we first formalize the effect of problem difficulty by quantifying the relationship between loss descent magnitude and rollout accuracy. Building on this analysis, we propose SEELE, a supervision-aided RLVR framework that dynamically adjusts problem difficulty to lie within the high-performance region. SEELE augments each training sample by appending a hint (part of a full solution) for difficulty reduction. Unlike previous hint-based approaches, SEELE deliberately computes the hint length for each individual problem to achieve an optimal difficulty. The optimal hint length is determined via multi-round rollout sampling, where an item response theory model fits accuracy–hint pairs from previous rounds to predict the next-round hint. This instance-level, real-time difficulty adjustment aligns problem difficulty with the evolving model capability, thereby improving exploration efficiency. Experiments show that SEELE outperforms Group Relative Policy Optimization (GRPO) and Supervised Fine-tuning (SFT) by +10.0 and +8.4 points, respectively, and exceeds the best prior supervision-aided approach by +3.8 points on average across six math reasoning benchmarks.

Recently several methods have shown promise for purely in silico “de novo” design of antibodies which bind to drug targets. The methods which have shown success in vitro propose candidates via either a generative diffusion model or hallucination-based sequence optimization, and then filter these candidates with a structure predictor model. Hallucination methods rely on compute-intensive backpropagation through a structure predictor model for each candidate, and the generative methods require expensive structure re-prediction and filtering of many (often mostly non-passing) candidates, limiting their application to test-time generation of large libraries. Given the highly variable per-drug-target hit rates of current methods, screening large libraries is a well established route to improved antibody candidate discovery. Thus, we propose an alternative approach, Bonobo, which instead formulates this problem as black-box optimization of a per-drug-target generative model, amortizing candidate generation into training. This is accomplished by using a structure predictor as a reward signal to directly train a GFlowNet generative model. We show that this approach can match or exceed the in silico metrics of state-of-the-art approaches, while allowing for dramatically more efficient generation of diverse and arbitrarily large numbers of antibody binder candidates.

Adversarial perturbation defenses protect images from generative editing by adding imperceptible noise. Yet none of these methods have been evaluated against AI nudification, despite AI-generated non-consensual intimate imagery (AIG-NCII) being among the most documented harms of generative AI and produced largely through inpainting. We argue this is a problem-formulation failure: prior threat models do not correspond to nudification attacks, and the misalignment is structural, spanning mask shape, prompt distribution, and success criterion which causes existing evaluations to systematically overestimate protection effectiveness. We reformulate adversarial inpainting protection around this documented harm. We introduce BodyBench, a benchmark of 648 fully synthetic clothed adult subjects, each paired with 11 mask variants spanning body, face, context, and dilation regions, along with nudification and redressing attack prompts. We propose three harm-aligned metrics: sexualization, naturalness, and recognizability that jointly determine whether an inpainted output constitutes a successful nudification attack. Auditing four recent protection methods (PhotoGuard, DiffusionGuard, AdvPaint, DiffVax) on BodyBench, we find that protection succeeds in only one configuration of one method, and only under exact mask alignment between defender and attacker---a condition no real defender can guarantee and one that we show is easily always bypassed. We also show that standard metrics such as PSNR are essentially uncorrelated with nudification protection. BodyBench makes this misalignment measurable and provides a foundation for defenses grounded in documented harm.

Large language models (LLMs) excel at reasoning across diverse domains, from mathematical problem-solving to code generation, yet struggle with strategic reasoning that requires long-term planning, opponent modeling and integrating tactical calculation with strategic understanding. Board games, with their fully observable states, perfect-information environments and objectively verifiable decisions, offer ideal testbeds for probing these capabilities. We introduce Board Game Arena (BGA), a multi-dimensional benchmark that evaluates LLMs' strategic reasoning along three cognitive axes—deductive, inductive, and abductive reasoning—through three challenging task types across five classic board games, yielding 45 sub-datasets with over one million samples. We evaluate 28 state-of-the-art LLMs on BGA and find that current models exhibit fundamental limitations in strategic reasoning for board games. While models demonstrate competence in understanding game rules and identifying legal moves, they struggle significantly with selecting optimal moves and applying strategic principles or tactical analysis. These results position BGA as a challenging and diagnostic benchmark for tracking progress in LLMs' strategic cognition.