TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI
Fields · this week
All fields3544Multimodal577Agents547Frontier LLMs482Inference & serving282Image segmentation202Graph learning178Learning verifiable rewards1683D scene168Voice AI101Forecasting time88Classifier & causal discovery88Flow matching76Evals60Teacher policy distillation55Adversarial training53All 32 fields

Open problems across fields

  • General in-context learning for embodied agents1 paper raises it · 0 address it

    Improving adaptability of models to new tasks and environments without task-specific fine-tuning is critical for scalable embodied intelligence.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Cost and latency in agentic systems2 papers raise it · 1 addresses it

    High computational and time costs limit practical deployment of agentic systems for real-world tasks.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
    • PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviewsraises · addresses
  • Physical-state verification and failure recovery1 paper raises it · 0 address it

    Robustness to irreversible failures and accurate state tracking are essential for reliable embodied control.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Evidence-grounded multimodal reasoning benchmarks1 paper raises it · 1 addresses it

    Current benchmarks often fail to ensure models use necessary audio-visual evidence, weakening evaluation reliability.

    • EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoningraises · addresses
  • Length generalization in sequential state tracking1 paper raises it · 1 addresses it

    Models struggle to maintain performance on problems much longer than their training data, limiting scalability.

    • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses

Named by an AI from these papers' abstracts.

Rising research topics

  • Training & fine-tuning42+90.9%
  • AI safety29+61.1%
  • Federated learning53+39.5%
  • Quantum machine learning29+38.1%
  • Computer vision29+31.8%
  • Evals60+25.0%
  • Code models13+18.2%
  • Forecasting time88+12.8%

Papers

  • arXiv cs.LGAI safetyOct 15

    Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths

    Joran Michiels, Anis Ismail, Maarten De Vos, Alejandro Sifrim

    Existing feature attribution methods that account for feature dependencies do not scale to high dimensions. We propose causal integrated gradients (CIG) and causal expected gradients (CEG), which extend integrated gradients to incorporate prior causal structure among input features while retaining its computational efficiency and, under conditions on the causal graph, its axiomatic guarantees. In many settings, some causal structure between features is already known, for example, that a transcription factor causally regulates a target gene's expression. Yet existing gradient-based methods cannot exploit this structure, instead crediting a feature's downstream effects over its true upstream cause, such as ranking the target gene above the transcription factor that regulates it. Our key idea is to embed this causal structure by routing the integration path along the causal graph. The method thereby decomposes each feature's attribution into a direct effect and effects mediated through its causal descendants. We evaluate CIG in three settings of increasing realism. First, on a synthetic benchmark with a known causal model, CIG's attributions best match the ground-truth causal effect…

    AI60PDF
  • arXiv cs.AIAgentsOct 15

    PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents

    Kshitij Mishra, Abhijith Sharma, Nils Lukas, Salem Lahlou

    Modern agentic systems extend language models with external tools, enabling them to complete complex tasks through multi-turn interactions. As these agents are deployed in consequential settings, they are often constrained by policies governing pricing, privacy, confirmation, safety, and other requirements. However, existing evaluation methods leave a critical gap: capability benchmarks measure what agents can accomplish, while content-safety red-teaming measures harmful generations, but neither tests whether agents comply with predefined policies during otherwise valid tool use. Such policy violations are difficult to audit because their effects may emerge only after several turns, span multiple tool calls, or surface in downstream systems. We propose PROBE (Policy Rule Observation via Behavioral Exploration), an algorithm for training LLM-based auditors that interact with deployed agents as realistic users and probe them for policy violations through multi-turn, tool-mediated dialogue. We formalize agent auditing as a two-player Markov game and propose a composite reward that balances violation discovery, behavioral plausibility, conversation progress, and policy diversity. To…

    AIAI safety80PDF
  • arXiv cs.LGOct 15

    Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery

    Xudong Zhang, Jianzhe Li, Yitong Tang, Peijie Zhou

    Genetic and drug perturbation screens are important tools for elucidating disease mechanisms and validating therapeutic targets, but experimental costs limit the number of candidates that can be tested. Existing perturbation screening methods typically update the surrogate model with feedback while keeping the acquisition function fixed, limiting their ability to adapt selection to different response landscapes. Experimental feedback reveals current hits and informs subsequent selection by updating candidate predictions, providing a training signal for learning how to select experiments. We formulate budgeted perturbation discovery as a sequential decision problem and propose Temporal Difference Active Learning (TDAL), which learns an acquisition function online through temporal difference learning from a single screening trajectory, accounting for current hits and future discoveries. TDAL uses the Hellinger distance between hit probabilities for unmeasured candidates before and after an experiment to weight successor value, and reuses measured outcomes through leave-batch-out (LBO) to construct virtual transitions and alleviate training data scarcity. Across eight public screens…

    AI20PDF
  • arXiv cs.LGComputer visionOct 15

    Scene Reconstruction Using Ubiquitous Wireless Signals via Diffusion Posterior Inference Over physics-Grounded Representations

    Vahid Yazdnian, Yasaman Ghasempour

    Knowing the layout of the physical world matters for many applications, yet the sensors we rely on for it (e.g., cameras and LiDAR) can fail in darkness, in adverse weather, or behind walls. Wireless signals do not face these limitations: every link between a base station and a user is shaped by the buildings it passes, reflects from, or is blocked by, leaving information about the surrounding scene embedded in the wireless channel measured at the endpoints. However, mapping channel measurements to the environment is a severely ill-posed problem: a measurement records only the structures that interact with the transmitted electromagnetic waves along its propagation paths, and even these observations can often be explained by multiple plausible scenes. We therefore formulate wireless scene reconstruction as posterior inference and develop a hierarchical framework with two complementary stages to approach this problem. A wireless foundation model, pretrained to respect propagation physics, transforms each channel measurement into a representation of the scene structure that shaped the observation. A diffusion model then jointly integrates representations from multiple measurements…

    AIMultimodal70PDF
  • arXiv cs.CLTraining & fine-tuningOct 15

    Unfragmenting Nawatl NMT: Single-Variant Specialization for Masewalkopa

    Luis A. Mercado-Campos, Alexis Palmer

    In minoritized (low-resource) language technologies, a common response to data sparsity is to aggregate text across multiple varieties and treat the combined data as a single corpus. However, mixed corpora of closely related indigenous variants can produce an artificial register that is accountable to no single speaker community, a structural failure we call variant fragmentation. This issue is acute for minoritized languages native to Mexico, such as Nawatl. Building on a 70,000-pair multi-variant foundation, we specialize an mT5-large checkpoint to Masewalkopa (nhn), the Nawatl variety spoken in Santa Ana Tlacotenco. We curate 2,665 parallel pairs, reserve all sentence-level data for evaluation, and incorporate 192 elder-transcribed target sentences via asymmetric backtranslation. A custom finite-state analyzer reduces unanalyzed surface forms from 82.0% to 19.9% and supplies functional syntax tags as plain-text prefixes, allowing the model to reuse existing subword embeddings rather than relying on frozen special tokens. The resulting LoRA-v9c-b model achieves 58.46 dev chrF++ and 58.20/57.90 directional test chrF++. Finally, CTranslate2 int8 quantization reduces CPU latency…

    AIProgramming languages50PDF
  • arXiv cs.ROOct 15

    DriveWorld3D Evidence Constrained 3D World Modeling and Generative Simulation for Real-World Autonomous Driving

    Wei Wang, Yiru Veronika Wang, Yihan Wang, Zihao Li, Xiaohui Liang

    Three dimensional modeling for autonomous driving must continuously estimate road geometry, obstacle occupancy, traffic participant behavior, and observational uncertainty under limited computational resources. Existing reconstruction methods can synthesize realistic novel views, but visual fidelity does not sufficiently characterize the geometric reliability required for driving. Generative world models can expand scenarios and predict future observations, yet may introduce content unsupported by measurements. We propose DriveWorld3D, a framework combining temporal video learning, measurement constraints from multiple sensors, and offline generative simulation. Its online component maintains a unified world state comprising road surfaces, volumetric occupancy, dynamic entities, and road relations, while separately representing physical occupancy, observability, and evidence provenance. Action conditioned future prediction and risk sensitive planning connect this representation to driving decisions. Its offline component reconstructs recorded scenes using neural radiance fields or 3D Gaussian Splatting, then expands long tail conditions using generative models while restricting…

    PDF
  • arXiv cs.CLInference & servingOct 15

    Patch where the text is new: a compression view of where byte-level models should spend compute

    Nicolás Vera Zúñiga

    Byte-level language models such as the Byte Latent Transformer (BLT) run their large global model once per patch and start a patch where a small model's next-byte entropy is high. This rule rarely starts a patch at in-line computed results, such as the number after "=" in a worked solution, and accuracy on them collapses under tight patch budgets. We propose novelty patching, motivated by LZ77-style compression: start a patch where the upcoming bytes are unlikely to repeat the recent context. The rule is a lookup table over the previous two bytes, fitted in seconds on raw text with no labels, reference model or losses. In BLT-style models trained from scratch on a 1.9 GB math corpus at a matched ~11% patch rate (3 seeds each), it has no clear effect at 1M parameters, raises final-answer accuracy from 47% to 72% at 12M, and at 50M raises computed-result accuracy from 21% to 57% and final-answer accuracy from 60% to 90%; a table fitted on the raw pretraining corpus keeps the gain. Outside math the advantage shrinks: novelty lowers bits per byte on prose and ties entropy on source code and on synthetic execution traces. An analysis of where boundaries fall explains the pattern.…

    AICode models60PDF
  • arXiv cs.LGMultimodalOct 15

    TIPS: A Tiny Inference-time Policy for Scaling in Diffusion Language Models

    Ya-Shi Zhang, Jian Tang, Pierre-André Noël, Oleksiy Ostapenko

    Masked diffusion language models expose an inference-time choice: which positions become visible after each denoising pass. Many existing decoding methods use hand-designed rules or require visibility to grow monotonically. We present a $\textbf{T}$iny $\textbf{I}$nference-time $\textbf{P}$olicy for $\textbf{S}$caling ($\textbf{TIPS}$), an approximately $600$K-parameter controller that learns both unmasking and remasking while keeping the underlying language model frozen. TIPS uses visibility-aware confidence features and a shallow transformer to select which tokens should be visible, while a fixed schedule controls the expected visible fraction. We train the controller through supervised warmup followed by reinforcement learning from terminal correctness rewards. On GSM8K and MATH-500 with LLaDA-8B-Instruct, the full-canvas and two-block TIPS variants achieve $58.46\%$ and $57.97\%$ micro-averaged accuracy at a budget of $32$ decoder evaluations, exceeding the strongest baseline in our main comparison by $12.1$ and $11.6$ percentage points, respectively. Both variants are trained at a budget of $32$ evaluations and remain competitive at higher budgets without retraining. These…

    AIInference & serving80PDF
  • arXiv cs.CVOct 15

    SCCL-DT: Semantic-Conflict-Aware Contrastive Learning with Dual-Rule Teacher Distillation for Zero-Shot Chest X-Ray Diagnosis

    Ting Liu, Haoran Lai, HaobinChen, Ming Liu, S Kevin Zhou

    Contrastive vision-language pre-training supports zero-shot chest X-ray diagnosis, but standard objectives treat every off-diagonal image-report pair in a batch as a negative. In radiology, recurring findings across patients mean that instance mismatch need not imply semantic incompatibility, creating false-negative supervision that we term a semantic conflict. A training-trace audit shows that pair-observations selected by the online mask used during training are enriched for report-derived finding agreement, although this proxy analysis does not establish clinical equivalence. Fixed thresholds can become miscalibrated as similarity distributions evolve, while soft reweighting leaves residual repulsive gradients. We therefore propose Semantic-Conflict-Aware Contrastive Learning (SCCL), which tracks modality-specific similarity distributions with exponential-moving-average (EMA) statistics, derives adaptive thresholds, and hard-masks flagged candidates before softmax normalization. Inclusive (OR) and consensus (AND) rules define two SCCL teachers, whose bidirectional cross-modal rankings are consolidated through standard distillation into a single deployable student, SCCL-DT.…

    AI10PDF
  • arXiv cs.CVOct 15

    Beyond the Dominant Label: Recovering Coexisting Lesion Evidence with Multiple Instance Learning

    Lubin Gan, Jing Zhang, Xinming Zhang, Chengpeng Xu, Siying Wu +1

    Whole-slide images may contain coexisting lesions, yet weak supervision typically provides only the most severe diagnosis. We formulate this setting as dominant-label multiple instance learning, where the observed label is the maximum-severity element of a latent lesion set. Standard multiclass MIL treats it as a complete one-hot description and therefore suppresses lower-severity evidence whenever it co-occurs with a dominant lesion. We propose DomSet-MIL, a label-aware framework that aligns the annotation mechanism across bag and instance levels. Dominant-Label Censored Likelihood models the reported diagnosis without declaring unreported lesions absent. Severity-Ordered Residual Routing assigns patch evidence from high to low severity and preserves residual support for secondary findings, while top-$q$ pooling links local routing scores to bag prediction. Experiments across natural and controlled settings show that DomSet-MIL achieves state-of-the-art performance in dominant-label prediction while more effectively recovering latent coexisting-lesion evidence. These findings demonstrate that modeling the dominant-label mechanism can improve diagnostic prediction without…

    AI10PDF
  • arXiv cs.SEOct 15

    Are We Testing the Wrong Quantum Bugs? A Study of Fault Representation Gaps in Quantum Software Testing

    Asif Mohammed Saad, Ahsanul Ameen Sabit, Jonah Brandenburgh, Jiyuan Wang, Qian Zhang +1

    Quantum software relies on compilers, intermediate representations, and execution frameworks that transform programs before execution. Faults in these components can change the behavior of otherwise correct quantum programs. Yet quantum testing techniques are often evaluated using mutation-generated faults and curated bug benchmarks. We investigate how well the faults represented by these artifacts reflect those encountered in modern quantum software. We audit four quantum mutation-testing tools and three curated bug benchmarks, and collect 410 verified bugs from ten quantum software repositories over two years. We classify faults from all three sources into a common taxonomy of 56 bug families and compare their representation across mutation operators, curated benchmarks, and recent real-world bugs. The mutation tools support 20 bug families, and curated benchmarks add 15 more. Yet only 56 of the 410 real-world bugs (13.7%) belong to families represented by either source; the remaining 354 (86.3%) belong to families absent from both. The largest unrepresented families concern compiler transformations (66 bugs), type handling (53), and input validation (47). Unlike local gate or…

    PDF
  • arXiv cs.CVOct 15

    Pathology foundation models for training-free case retrieval in salivary gland tumors

    Maximilian J. Roesel, Niklas Kiermeyer, Philipp Keyl, Frederick Klauschen

    In pathology, pattern recognition relies on a frame of reference built through extensive training and experience, which may still fall short when encountering rare cancer subtypes. Archives of previously diagnosed tumors often contain relevant precedents, yet identifying the most relevant cases remains challenging. Here we explore whether content-based retrieval with current pathology foundation models facilitates rare cancer diagnostics without any task-specific training. Pathologists can query a digitized archive using a region of interest (ROI) from a whole slide image (WSI) and retrieve morphologically similar cases, along with their ICD-O codes and corresponding WSIs. The ROI can be selected manually or automatically using a gated attention-based multiple instance learning model. We evaluate our approach by leave-one-case-out on an imbalanced dataset of 137 salivary gland tumor cases spanning 12 ICD-O morphology categories, comparing four pathology foundation models (Atlas2, Atlas2-B, Atlas2-S, and UNI2h). Top-1/3/5 retrieval was 62.5%/76.7%/81.3% for Atlas2, 50.2/66.6/72.9% for UNI2h, 52.3%/71.5%/77.6% for Atlas2-B and 54.4/65.2/73.7% for Atlas2-S. Macro-averaged F1 ranged…

    AI10PDF
  • arXiv cs.CLTraining & fine-tuningOct 15

    Multi-SFT: Permissively-Licensed Multilingual Instruction-Following

    Daniela Baiamonte, Kamyar Zeinalipour, Elena Fano, Stefano Simonazzi, Andrea Zugarini

    Supervised fine-tuning datasets remain overwhelmingly English-centric and commercially restricted, as their content is frequently generated by proprietary models whose terms of service forbid training competing systems. We introduce Multi-SFT, a commercially permissive collection of 502,818 instruction-response pairs across five European languages, built via translation and regeneration pipelines for tasks where translation is insufficient. Human evaluation yields inter-annotator agreement of at least 0.87 across all datasets and languages. Fine-tuning nine models from three different families (EuroLLM, OLMo 2, Qwen3; 1B-32B) and evaluating them on 13 benchmarks shows that Multi-SFT alone is competitive with larger augmented mixes and official instruction-tuned releases, with decisive advantages on safety tasks.

    AIEvals80PDF
  • arXiv stat.MLRoboticsOct 15

    Learning Changes the World and Then What Was Learned has Changed: Training and Deploying Neural Networks in the Control Loop

    Vittorio Lippi

    Neural networks offer critical adaptability for controlling complex systems where nominal modeling proves intractable. However, when offline-trained neural networks are deployed within closed-loop control systems, their actions fundamentally alter the state distribution upon which they were trained. This paper introduces a unified taxonomy to categorize these sequential failure modes: the initial Closed-Loop Identification Error, the deployment-induced Action Error, and the continuous Tracking Error. Through discrete-time sensitivity analysis, this work formalizes how offline-learned parameters locally guarantee a trajectory divergence upon deployment, degrading performance due to local loss geometry. To mitigate this distribution shift, we propose actionable design policies centered on time-scale separated online adaptation. These mechanisms are validated through ablation studies on a nonlinear Duffing oscillator, demonstrating that bounded continuous learning successfully mitigates trajectory divergence whereas static deployments fail, offering concrete guidelines for practitioners deploying machine learning components in safety-critical feedback systems.

    AITraining & fine-tuning60PDF
  • arXiv cs.AITraining & fine-tuningOct 15

    Learning from Unverified Peers via Shared Residual Distillation

    Feiyang Chen, Runze Ma, Zichen Wang, Jiong Lou, Zihan Wang +2

    A language model can generate several solutions to the same problem, some leading to correct answers and others to incorrect ones. Many post-training methods turn these trajectories into learning signals using supervision from reference answers, verifiable feedback, or external teachers. Without such supervision, learning from the model's own generations becomes less straightforward, as their correctness cannot be reliably assessed. An incorrect solution may nevertheless contain useful intermediate reasoning, so its value as supervision need not be determined solely by its final answer. Can a model improve by learning from its unverified peer solutions without first determining which are correct? We propose Shared Residual Distillation (SRD), an on-policy self-distillation method that learns from the model's own unverified peer trajectories. SRD compares how peers change the prediction distribution relative to a control, retaining adjustments that agree in direction and are conservative in magnitude. This yields supervision without treating any complete solution as correct, and the trained model requires no peers at inference time. Starting from the corresponding base models, SRD…

    AI70PDF
  • arXiv cs.LGOct 15

    Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones

    Nathan Chalumeau, Xavier Renard, Remi Meynadier, Hugo Rakotoarimanga, Marcin Detyniecki +1

    Weather prediction is undergoing an important shift, with data-driven AI models outperforming leading numerical weather prediction systems on average at a fraction of the computational cost. Yet, whether this success extends to extreme events remains contested. Earlier evaluations have exposed important shortcomings, but have largely focused on deterministic models and metrics, leaving the capabilities of the latest probabilistic models less understood. We conduct an extensive benchmark of tropical cyclone forecasting, comparing GenCast, FourCastNet 3, and FGN with ECMWF's operational physics-based ensemble, IFS-ENS. We develop a suite of probabilistic metrics and diagnostic analyses to assess cyclone tracking, intensity biases, uncertainty, and the wind-pressure relationship that characterizes storm structure. We find that, despite remaining limitations in intensity and ensemble spread, leading AI models substantially outperform IFS-ENS in cyclone tracking: FGN achieves better probabilistic location scores for 90% of evaluated storms in 2025. Further analyses reveal model-specific failure modes and suggest a lingering influence of pretraining data, pointing to opportunities for…

    AI10PDF
  • arXiv cs.CVMultimodalOct 15

    Retrofitting Recurrent Vision-Language Models from Pretrained Backbones

    Madhav Iyengar, Andreas Geiger, Hilde Kühne

    Recent work shows that depth recurrence can be retrofitted into pretrained language models. In this work, we adapt this paradigm for visual understanding, using depth recurrence to reduce the parameter footprint of a pretrained vision-language model (VLM). To this end, we prune layers from the language backbone of the VLM and loop over a subset of the remaining layers. At each step of the loop, a linear adapter merges the block's output with the token representations from the preceding layers and projects the fused representation back into the block. As the pruning impacts the original model performance, we propose a three-stage recovery training: first, we leverage a language-only pretraining to recover the performance of the language backbone, followed by an alignment of the vision-language projector, and a full fine-tuning of the model via visual instruction tuning. In the first and the last stage, we distill the outputs of the pretrained non-recurrent model into the recurrent model, which further improves the recovery. We evaluate the proposed approach on the TinyLLaVA-1.4B backbone without introducing any new vision-language data during retrofitting. Our experiments…

    AITraining & fine-tuning80PDF
  • arXiv cs.CLProgramming languagesOct 15

    The Right Byte First: How UTF-16 Helps Multilingual Boundary Prediction

    Hyunsik Kim

    Many hierarchical byte-level language models group bytes into patches using a learned boundary predictor whose view of the next codepoint depends on encoding and lookahead. In UTF-8, codepoints of many scripts take three bytes: 8 of 24 bits mark length and continuation, and the first byte carries only 4 high codepoint bits. After the same left context, a mark extending a grapheme cluster and a letter starting the next can thus share their first byte. Universal Byte-Level Encoding (UBE) keeps one- and two-byte UTF-8 encodings but writes these codepoints as two UTF-16 bytes, low byte first, so its first symbol carries 8 low codepoint bits that can distinguish such continuations. We train small causal predictors on matched FineWeb-2 text and evaluate on FLORES-200 under UTF-8, UBE, and UBE's same-length big-endian variant. At one-symbol lookahead, balanced grapheme-boundary error at codepoint boundaries across 17 languages in 13 Brahmic scripts is 8.76% with UTF-8, 8.62% with the big-endian variant, and 0.06% with UBE. When the target instead retains a parent tokenizer's subword cuts at grapheme boundaries, UBE lowers the mean error relative to UTF-8 at the same lookahead by 72.91%…

    AI50PDF
  • arXiv cs.CVMultimodalOct 15▲ 8

    Memory as Weights: Internalizing Long-Term History for Streaming Videos

    Zhuoming Liu, Jinhong Lin, Lin Zhang, Yiwu Zhong, Yin Li

    Streaming vision-language models (VLMs) must continuously integrate information from the past while remaining responsive to current observations and user queries. Existing memory mechanisms typically compress, retrieve, or cache historical observations and reintroduce them into the input context, forcing historical memory and current observations to compete for limited context. We propose MaLoW, a streaming memory framework that instead internalizes historical context into evolving lightweight parameter updates. MaLoW uses a recurrent HyperNetwork to incrementally consolidate incoming video observations into fixed-size LoRA weights, allowing historical information to be carried forward without revisiting the full video stream. In doing so, MaLoW represents history as weights, while keeping the current observation as input. To support training, we further construct MaLoW-Instruct, a large-scale streaming video dataset containing 381K question-answer pairs over 56K videos. We conduct extensive experiments to demonstrate that MaLoW achieves strong performance on OVO-Bench, StreamingBench, and StreamArena. On the backward split of OVO-Bench, MaLoW outperforms prior memory approaches…

    AIInference & serving80Code
  • arXiv cs.AIAI safetyOct 15

    When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models

    Wei Cai, Jian Zhao, Yuchen Yuan, Xuelong Li

    Multimodal large language models (MLLMs) can act unsafely when individually benign images and texts are interpreted jointly. Beyond implicit reasoning risk, where reasoning drifts toward harm, we identify intent-level risk, where cross-modal ambiguity silently commits the model to a hazardous premise that path-level optimization alone cannot correct. We propose SAFE-PRO, which uses a Risk-Conditioned Uncertainty (RCU) signal, combining predictive entropy with a learned cross-modal risk score, to decide when to ask safety-grounded clarifying questions and where to apply path optimization, under a reward that prioritizes safety and penalizes over-refusal. We also build SSUI-Dialog, a multimodal multi-turn dataset with dual-intent supervision, and theoretically analyze gradient variance and unsafe-completion risk under RCU. Across seven benchmarks and two base MLLMs, SAFE-PRO consistently improves safety over SRPO, roughly halves its over-refusal, and surpasses GPT-4o and Claude-3.5-Sonnet in average single-turn safety.

    AIMultimodal90PDF
Load more
PDF