Peer review, the bedrock of scientific advancement in machine learning (ML), is strained by a crisis of scale. Exponential growth in manuscript submissions to premier ML venues such as NeurIPS, ICML, and ICLR is outpacing the finite capacity of qualified reviewers, leading to concerns about review quality, consistency, and reviewer fatigue. This position paper argues that AI-assisted peer review must become an urgent research and infrastructure priority. We advocate for a comprehensive AI-augmented ecosystem, leveraging Large Language Models (LLMs) not as replacements for human judgment, but as sophisticated collaborators for authors, reviewers, and Area Chairs (ACs). We propose specific roles for AI in enhancing factual verification, guiding reviewer performance, assisting authors in quality improvement, and supporting ACs in decision-making. Crucially, we contend that the development of such systems hinges on access to more granular, structured, and ethically-sourced peer review process data. We outline a research agenda, including illustrative experiments, to develop and validate these AI assistants, and discuss significant technical and ethical challenges. We call upon the ML community to proactively build this AI-assisted future, ensuring the continued integrity and scalability of scientific validation, while maintaining high standards of peer review.
论文检索
输入标题、作者或关键词，从 13,033 篇学术成果中精准定位
Social Aspects · Accountability, Transparency, and Interpretability
Peer review, the bedrock of scientific advancement in machine learning (ML), is strained by a crisis of scale. Exponential growth in manuscript submissions to premier ML venues such as NeurIPS, ICML, and ICLR is outpacing the finite capacity of qualified reviewers, leading to concerns about review quality, consistency, and reviewer fatigue. This position paper argues that AI-assisted peer review must become an urgent research and infrastructure priority. We advocate for a comprehensive AI-augmented ecosystem, leveraging Large Language Models (LLMs) not as replacements for human judgment, but as sophisticated collaborators for authors, reviewers, and Area Chairs (ACs). We propose specific roles for AI in enhancing factual verification, guiding reviewer performance, assisting authors in quality improvement, and supporting ACs in decision-making. Crucially, we contend that the development of such systems hinges on access to more granular, structured, and ethically-sourced peer review process data. We outline a research agenda, including illustrative experiments, to develop and validate these AI assistants, and discuss significant technical and ethical challenges. We call upon the ML community to proactively build this AI-assisted future, ensuring the continued integrity and scalability of scientific validation, while maintaining high standards of peer review.
Deep Learning · Robustness
Multimodal large language models (MLLMs) have achieved remarkable progress, yet the object hallucination remains a critical challenge for reliable deployment. In this paper, we present an in-depth analysis of instruction token embeddings and reveal that they implicitly encode visual information while effectively filtering erroneous information introduced by misleading visual embeddings. Building on this insight, we propose the Instruction Lens Score (InsLen), which combines a Calibrated Local Score with a Context Consistency Score that measures context consistency of the object tokens. The proposed approach serves as a plug-and-play object hallucination detector without relying on auxiliary models or additional training. Extensive experiments across multiple benchmarks and diverse MLLM architectures demonstrate that InsLen consistently outperforms existing hallucination detection methods, highlighting its effectiveness and robustness. The code will be publicly available.
Deep Learning · Robustness
Vision-language models (VLMs) have progressed rapidly with large-scale high-quality data and adaptation strategies, yet remain brittle under real-world corruptions, where both visual recognition and language-grounded reasoning degrade. Beyond cascaded image restoration, a natural alternative is parameter-efficient adaptation that aligns corrupted features with clean references; however, Euclidean alignment alone is not semantics-preserving and can even harm downstream reasoning. We attribute this to a semantic misalignment gap, where features become geometrically closer while drifting off the in-distribution support on which multimodal reasoning is calibrated. To address this, we propose Manifold-Adversarial Adapters (MAA), lightweight layer-wise modules for a frozen vision encoder that explicitly steer corrupted features back onto the clean in-distribution manifold rather than merely shrinking feature-space distance. MAA combines paired feature self-distillation with a token-level adversarial manifold constraint to prevent off-manifold semantic shortcuts. At inference, only the adapters are retained, enabling single-stage robustness with negligible overhead and avoiding the latency and semantic drift of restoration pipelines. Across benchmarks and corruption settings, MAA consistently improves performance over strong baselines.
Applications · Health / Medicine
Reinforcement learning has driven the mass adoption of large language models by unlocking unexpected capabilities, yet this approach remains largely underexplored for generative DNA models. We investigate whether similar post-training techniques can induce emergent biological realism in DNA language models, using plasmid generation as a testbed due to plasmids' relative simplicity, well-characterized functional constraints, and ubiquity in biotechnology. Using Group Relative Policy Optimization with a reward function based on constraints from engineered biology, our model achieves a 77\% quality control pass rate compared to 5\% for the pretrained baseline. Remarkably, beyond explicitly optimized features, the model exhibits surprising biological parallels: generated sequences match natural plasmids in thermodynamic stability, codon usage patterns, and ORF length distributions, properties not explicitly optimized in the reward function. These results suggest that RL post-training can steer DNA language models toward biologically coherent regions of sequence space, analogous to how such techniques unlock unexpected capabilities in natural language models, particularly in verifiable domains.
Deep Learning · Generative Models and Autoencoders
Text-to-video diffusion transformers encode semantic information unevenly across model depth, which constrains effective concept erasure. We identify a representational bottleneck, termed concept–layer topological alignment, under which target concepts exhibit higher separability at certain representational depths. Outside these depths, concept and non-target signals remain strongly entangled, limiting the effectiveness of depth-specific erasure. This observation reframes concept erasure as the problem of identifying representational depths where concept–non-target separation naturally emerges. Motivated by this structural constraint, we introduce CLEAR, a separability-driven optimization framework for concept erasure that explicitly enforces concept–layer alignment. CLEAR operationalizes this principle by formulating layer selection as an optimization problem over concept–non-target separability, rather than relying on layer-agnostic or heuristic choices. To enable this, we introduce a separability-aware objective that favors layers exhibiting stronger concept–non-target separation. Experiments on large-scale text-to-video diffusion models demonstrate that enforcing concept--layer alignment leads to more precise concept suppression while preserving overall generative quality.
Applications · Everything Else
This paper introduces BioAgent Bench, a benchmark dataset and an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks. The benchmark contains curated end-to-end tasks (e.g., RNA-seq, variant calling, metagenomics) with prompts that specify concrete output artifacts to support automated assessment, including stress testing under controlled perturbations. We evaluate frontier closed-source and open-weight models across multiple agent harnesses, and use an LLM-based grader to score pipeline progress and outcome validity. We find that frontier agents can complete multi-step bioinformatics pipelines without elaborate custom scaffolding, often producing the requested final artifacts reliably. However, robustness tests reveal failure modes under controlled perturbations (corrupted inputs, decoy files, and prompt bloat), indicating that correct high-level pipeline construction does not guarantee reliable step-level reasoning. Finally, because bioinformatics workflows may involve sensitive patient data, proprietary references, or unpublished IP, closed-source models can be unsuitable under strict privacy constraints; in such settings, open-weight models may be preferable despite lower completion rates. We release the dataset and evaluation suite publicly.
Social Aspects · Security
Large Language Models (LLMs) have become critical to modern software development, but their reliance on uncurated web-scale datasets for training introduces a significant security risk: the absorption and reproduction of malicious content. This risk materialized in November 2024, when a user suffered a \$2,500 financial loss after executing code generated by ChatGPT that contained a live scam phishing URL. To systematically evaluate this risk, we introduce Scam2Prompt, a scalable automated auditing framework that identifies the underlying intent of a scam site and then synthesizes developer-style prompts that mirror this intent, allowing us to test whether an LLM will generate malicious code in response to these prompts. In a large-scale study of four production LLMs (GPT-4o, GPT-4o-mini, Llama-4-Scout, and DeepSeek-V3), we found that Scam2Prompt's developer-style prompts triggered malicious URL generation in 4.24% of cases. To test the persistence of this security risk, we constructed Innoc2Scam-bench, a benchmark of 1,377 prompts that consistently elicited malicious code from all four LLMs. When applied to seven additional production LLMs released in 2025, we found the vulnerability is not only present but severe, with malicious code generation rates ranging from 12.9% to 47.3%. Furthermore, existing safety measures like state-of-the-art guardrails or RAG-based agents proved insufficient to prevent this behavior.
Probabilistic Methods · Bayesian Models and Methods
Multi-objective Bayesian optimization (MOBO) provides a principled framework for optimizing expensive black-box functions with multiple objectives. However, existing MOBO methods often struggle with coverage, scalability with respect to the number of objectives, and integrating constraints and preferences. In this work we propose STAGE-BO, Sequential Targeting Adaptive Gap-Filling $\varepsilon$-Constraint Bayesian Optimization, that explicitly targets under-explored regions of the Pareto front. By analyzing the coverage of the approximate Pareto front, our method identifies the largest geometric gaps. These gaps are then used as constraints, which transforms the problem into a sequence of inequality-constrained subproblems, efficiently solved via constrained expected improvement acquisition. Our approach provides a uniform Pareto coverage without hypervolume computation and naturally applies to constrained, and preference-based settings. Experiments on synthetic and real-world benchmarks demonstrate superior coverage and competitive hypervolume performance against state-of-the-art baselines.
Deep Learning · Generative Models and Autoencoders
Naive application of token-wise temperature scaling alters the maximum a posteriori (MAP) estimate at the sequence level, degrading model performance. This issue is exacerbated in MDMs, which estimate sequence-level likelihoods with high variance under different unmasking orders. In this paper, we address the challenge of reliable temperature scaling with a novel fine-tuning procedure and introduce a new metric to measure effective temperature scaling without requiring the partition function. Our method adapts a context-dependent sequence-level temperature scaling method to any-order generative models, such as MDMs. And introduces two new, more stable learning objectives. We achieve this by computing the expected probability of a given sequence under different unmasking orders. Our experiments on language models (bd3lm) show that this leads to more consistent generation, with lower perplexity and lower generation variance.
Applications · Health / Medicine
Modern high-throughput biological datasets containing thousands of perturbations enable large-scale discovery of causal graphs that represent regulatory interactions between genes. Differentiable causal graphical models and regression-based methods have been developed to infer gene regulatory networks (GRNs) from interventional datasets. However, existing approaches fail to capture the non-linear dynamics of biological processes such as cellular differentiation. To address this limitation, we propose \textit{PerturbODE}, a novel framework that employs interpretable neural ordinary differential equations (neural ODEs) to model cell state trajectories under perturbations and derive the underlying causal GRN from the neural ODE parameters, enabling downstream simulation of unseen genetic interventions. The GRN is encoded via a single-hidden-layer feedforward network, implicitly grouping genes into interpretable co-regulated modules. We demonstrate PerturbODE's efficacy in GRN inference and extension to perturbation response prediction across both simulated and real overexpression datasets.
Applications · Health / Medicine
Recent advances in diffusion models show promise for Structure-Based Drug Design (SBDD), which aims to generate 3D ligand molecules that bind tightly to specific protein targets. This involves jointly optimizing the ligand's 3D conformation and its binding position within the protein pocket. However, existing diffusion-based SBDD methods diffuse conformation and binding position simultaneously within a high-dimensional joint space, leading to inefficient exploration and suboptimal generation quality in both aspects. To address this, we propose **DeCoDe**, a novel diffusion framework that **decouples** the diffusion processes of the binding position and molecular conformation. Our key insight is to prioritize the perturbation of the ligand's internal conformation in the early stages of the forward (noising) process, while accelerating the perturbation of its global binding position later. This design guides the reverse (denoising) process to *first coarsely position* the ligand within the pocket before \textit{refining its detailed structure}, mimicking a more efficient, step-wise generation strategy. Extensive experiments on the CrossDocked2020 benchmark show that DeCoDe achieves significantly higher structural fidelity (with an average improvement of 18%), while maintaining competitive binding affinity and overall molecular properties compared to state-of-the-art baselines. Code will be released after acceptance.
Deep Learning · Robustness
Safety alignment of large language models is fragile: even small fine-tuning perturbations elastically revert behaviors toward those of the pre-training, with degradation inversely proportional to the size of the alignment set. We ask how to achieve safety alignment with \emph{minimal augmentation}. To this end, we model augmentation as a set of group actions on sequences and formalize robustness gains as a normalized, monotone submodular function over transformations. We then leverage submodular optimization to select minimal augmentations that provably improve robustness. Experiments confirm that our approach efficiently restores safety alignment while minimizing the overhead of augmentation.
Deep Learning · Robustness
Multimodal alignment fails under deployment shift because standard objectives entangle cross-modal dependence with marginal-sensitive geometry. Stable Spectral Copula Alignment (SSCA) provides a deployment protocol targeting copula-stable dependence under strictly monotone marginal distortions, with auditable, label-free diagnostics for monitoring and mitigation. SSCA combines (i) clipped soft-rank Gaussianization suppressing marginal effects while tracking tie/approximation errors, (ii) dependence-weighted sliced Wasserstein hub coupling for globally coherent multiway alignment with cycle auditing, and (iii) diagonal-stabilized block-spectral learning with eigengap-normalized Davis--Kahan diagnostics, yielding an actionable subspace-risk inequality. A calibrated gate maps diagnostic proxies to a reliability signal with controlled false-alarm/miss rates, enabling safe activation, budgeted remediation, and conservative fallback for out-of-scope drift. Evaluations on MOSEI/MELD, MSCOCO, and CC3M-500K demonstrate improved performance under perturbation and substantially reduced degradation under both monotone and realistic drifts.
Deep Learning · Robustness
Large-scale web-harvested datasets have fueled the progress of cross-modal retrieval but inevitably suffer from \textit{noisy correspondence}, which severely degrades model generalization. Existing methods primarily address this by filtering out noise or seeking a substitute label, yet they predominantly remain bound by a ``Discrete Selection'' paradigm. We argue that relying on a single discrete proxy induces \textit{Single-Point Fragility} and \textit{Discretization Error}. To overcome these limitations, we propose a novel framework, \textbf{Intra-modal Neighbor-based Rectification (IN$^2$R)}, which shifts the paradigm from searching for a substitute to \textit{synthesizing} a reliable supervision target. Leveraging the intrinsic geometric stability of intra-modal data, IN$^2$R employs a \textbf{Graph Refiner} to perform relational reasoning over neighbors retrieved from a dynamic \textbf{Cross-Model Memory}. Instead of propagating discrete labels, our method synthesizes a continuous, soft prototype that reflects the consensus of the local semantic neighborhood, effectively rectifying inter-modal misalignment. Extensive experiments on Flickr30K, MS-COCO, and CC152K demonstrate that IN$^2$R significantly outperforms state-of-the-art methods.
Applications · Computer Vision
Deep learning–based watermarking has substantially improved robustness to real-world noise, but its performance degrades as the payload dimension increases. In contrast, coding-based methods such as quantization index modulation (QIM) do not suffer from this curse of dimensionality, although they are less robust to real-world noise. To leverage the strengths of both approaches, we propose OrthoMark, a framework that decouples robust feature extraction from message encoding. OrthoMark first learns a distortion-invariant feature representation using a deep robust feature extractor, and then performs watermark encoding and decoding in this feature domain using coding-based methods. Extensive experiments demonstrate that OrthoMark significantly improves the trade-off among visual quality, robustness, and capacity compared to prior deep watermarking methods, with particularly large gains in the high capacity regime, effectively overcoming the curse of dimensionality.
Deep Learning · Graph Neural Networks
Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While Graph Neural Networks (GNNs) are the standard solution, state-of-the-art pipelines often rely on explicit structural heuristics or memory-intensive node embeddings—approaches that struggle to generalize or scale to massive graphs. Emerging Graph Transformers (GTs) offer a potential alternative but often incur significant overhead due to complex structural encodings, hindering their applications to large-scale link prediction. We challenge these sophisticated paradigms with PENCIL, an encoder-only plain Transformer that replaces hand-crafted priors with attention over sampled local subgraphs, retaining the scalability and hardware efficiency of standard Transformers. Through experimental and theoretical analysis, we show that PENCIL extracts richer structural signals than GNNs, implicitly generalizing a broad class of heuristics and subgraph-based expressivity. Empirically, PENCIL outperforms heuristic-informed GNNs and is far more parameter-efficient than ID-embedding–based alternatives, while remaining competitive across diverse benchmarks—even without node features. Our results challenge the prevailing reliance on complex engineering techniques, demonstrating that simple design choices are potentially sufficient to achieve the same capabilities.
Social Aspects · Safety
Conversational assistants are increasingly integrating long-term memory with large language models (LLMs). This persistence of memories, e.g., the user is vegetarian, can enhance personalization in future conversations. However, the same persistence can also introduce safety risks that have been largely overlooked. Hence, we introduce \textbf{PersistBench} to measure the extent of these safety risks. We identify two long-term memory-specific risks: \textit{cross-domain leakage}, where LLMs inappropriately inject context from the long-term memories; and \textit{memory-induced sycophancy}, where stored long-term memories insidiously reinforce user biases. We evaluate 18 frontier and open-source LLMs on our benchmark. Our results reveal a surprisingly high failure rate across these LLMs - a median failure rate of $53\%$ on cross-domain samples and $97\%$ on sycophancy samples. To address this, our benchmark encourages the development of more robust and safer long-term memory usage in frontier conversational systems.
Deep Learning · Robustness
Large language models (LLMs) can be influenced by harmful or irrelevant context, which can significantly harm model performance on downstream tasks. This motivates principled designs in which LLM systems include built-in mechanisms to guard against such "garbage in, garbage out" scenarios. We propose a novel approach to limit the degree to which harmful context can degrade model performance. First, we define a baseline "safe" behavior for the model -- the model's performance given no context at all (zero-shot). Next, we apply distribution-free risk control (DFRC) to control the extent to which the user-provided context can decay performance below this safe zero-shot baseline. We achieve this by leveraging dynamic early exit prediction, ignoring later attention heads that attend the most to the unsafe inputs. Finally, we propose modifications to DFRC that allow it to both control risk for harmful inputs \textit{and} leverage performance and efficiency gains on helpful inputs. We present both theoretical and empirical results across 9 tasks spanning in-context learning and open-ended question answering, showing that our approach can effectively control risk for harmful context and simultaneously achieve substantial computational efficiency gains with helpful context.
General Machine Learning · Causality
We present a regression-adjustment framework designed to estimate longitudinal treatment effects in randomized experiments under static regimes. Although regression-adjustment methods are useful for variance reduction in randomized experiments through the use of pre-treatment covariates, they usually focus only on average effects, which cannot capture valuable knowledge about when effects appear and how long they continue. To address this limitation, we need to consider intermediate outcomes and evolving post-treatment covariates over time, and we represent these transitions using transition kernels. Furthermore, we establish the asymptotic normality and the semiparametric efficiency bound for our estimator, enabling more powerful statistical inference. Simulation studies and empirical analysis using A/B test data from a streaming platform in Japan demonstrate the practical advantages of our method.