paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialogue

Shibo Wang, Zicheng Zhang, Libo Wang, Junfeng Ma

LLM-based full-duplex voice services allow users to speak while the assistant is responding. Because servers can generate output and advance dialogue state faster than clients can play it, subsequent user speech may be interpreted based on content the user never heard. We call this failure Generative Context Mis-anchoring (GCM). To address GCM issues, we present PACE, a provider-independent middleware layer that anchors model-facing context to the client playback boundary, a system-observable proxy for what the user could have heard. After an interruption, PACE repairs this context to exclude assistant content that never reached playback, while preserving low-latency generation across heterogeneous voice runtimes. We implement PACE's audio-only projection path end to end in a browser-based realtime voice assistant using a black-box speech model, without modifying the model service. We also construct GCM-Bench, a new controlled benchmark dataset of 108 playback-relative referent-anchoring cases. On GCM-Bench, PACE raises Referent Anchoring Accuracy from 25.0% to 96.3% over a cancellation-only baseline. On 200 Full-Duplex-Bench v1 interruption samples, it preserves interruption response quality. These results show that grounding model-facing context in actual playback is a practical way to maintain consistency in full-duplex voice dialogue.

arXiv

TeXFix-Bench: An Empirically Grounded Multi-Format Benchmark for LLM-Based Document Source Repair

Prajwal S. Venkateshmurthy

Scientific and technical writing depends on markup sources that must compile: LaTeX, Typst, and Markdown pipelines fail on missing delimiters, mismatched environments, broken imports, or package conflicts. Existing document-repair evaluations inject faults with ad-hoc edits that lack an empirical fault model. We present TeXFix-Bench, a multi-format benchmark for LLM-based full-source document repair grounded in a mined fault taxonomy. A Grounded-Theory study of localized hard-crash LaTeX faults from TeX Stack Exchange, GitHub commits, and package documentation (168 verified faults, dual open coding at $κ$=0.34) yields an 18-category taxonomy instantiated as DocMut: 48 AST-aware operators across three formats. A three-model cross-benchmark shows DocMut faults are 5.6-9.2 pp harder to repair than pattern-based mutations on the same seeds, and a real-error case study (88 mined human crashes, 67.0% repair success) brackets both synthetic sets from below. We construct 10,437 instances from 743 openly licensed seeds and evaluate seven LLMs under a fixed zero-shot protocol with provider-pinned routing, collecting 48,651 attempts at about USD 200 total inference cost. A complete 6,613-instance x 7-model balanced matrix confirms all rankings. A pinned engine gate yields a 27.5-point intention-to-treat compile spread (56.7-84.2%). Typst is markedly harder than LaTeX and Markdown. A restoration oracle over 28,129 compiling repairs shows that 13.6-18.5% of compiling repairs materially alter document text, and restoration rank diverges from compile rank: the model with the lowest compile rate restores content best among its successes. Compile success alone overstates repair quality. We release the taxonomy, DocMut, and all campaign artifacts.

arXiv

Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks

Boxiu Li, Zimo Wen, Yijia Fan, Chuan Wen, Fan Yang, Hangxi Guo, Jiaao Wu, Jiachen Zhang, Junxiang Lei, Mukai Li, Ruize Tang, Runjing Gu, Shibo Hu, Sihan Chen, Sufeng Guo, Wanbo Zhang, Xian Zhang, Xiaoyu Chen, Xuanhe Zhou, Xuyao Huang, Yifei Gao, Yifei Shen, Yilin Chen, Yuheng Wu, Yuzhe Zhang, Zelong Zhao, Zhijie Deng

Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and pivot when measurements reveal failure, hidden constraints, or a misspecified objective. We present Argus, a persistent, self-evolving runtime in which Manager, Planner, Engineer, and Reviewer execute bounded missions over durable project state. Argus separates stable user intent from operational objectives, constraints, and verification criteria, and admits memories, skills, procedures, verifiers, routing decisions, and rejected routes only after role-owned review and, when available, task-native verification. Model weights remain fixed; self-evolution occurs through persistent runtime state and control policy, with autonomous execution between operator-owned escalation points. Across seven GPT-5.5 benchmark arenas, Argus achieves about 78% on SWE-Bench Pro versus 59% for Direct Copilot while using 1.41 times the aggregate tokens. After verification-gated self-evolution, mature SWE-Bench waves use 21% fewer solve-input tokens and 15% less active workflow time per task than startup waves, while recording 34 verifier recoveries and 22 strict review-loop rescues. Argus also reaches 76.8% on AARRI-Bench and a 28.0-point gap on mathematical data synthesis, with competitive GPU-kernel and language-model-training results. Beyond benchmarks, an optimized RWKV6 kernel was merged upstream; a multi-day mathematics campaign retained falsified routes and proof-backed frontier updates; and six paper pipelines completed 254 missions with 16 stage rollbacks. These results show that a fixed-weight, self-evolving harness can revise, recover, and accumulate verified approaches while producing structured trajectories for future supervised and reinforcement learning.

arXiv

From Errors to Rules: Iterative Prompt Optimization for Text Classification

Yueying Cui, Renhao Xue, Yi Zhang, Mukul Prasad

Prompt optimization for text classification spans diverse approaches, from demonstration selection to exploration-based search to error-driven diagnosis, each with known but incompletely characterized strengths and limitations. We conduct a comprehensive empirical study across diverse classification benchmarks (2 to 150 classes) comparing these paradigms through both quantitative evaluation and qualitative analysis of optimization traces, revealing that each paradigm excels on structurally different task types and that no single method dominates. Guided by these insights, we propose Error-Guided Optimization (ERGO), an error-driven method that iterates over the full training set in non-overlapping batches, diagnoses classification failures, and generates targeted decision rules through a diagnose-prescribe-rewrite feedback loop. ERGO achieves the best accuracy on tasks where errors concentrate in specific confused label pairs (which we term boundary-learnable tasks): TREC: 90.0%, CLINC150: 94.4%, converges in 3-5 iterations, and produces interpretable decision rules. While ERGO does not achieve the highest overall average, it fills a complementary role: demonstration-based ICL wins on coverage-dependent tasks, exploration-based search wins on many-class intent, and ERGO wins where decision boundaries are learnable from error patterns. We provide a complementarity framework linking task characteristics to optimal paradigm selection, offering practical guidance for practitioners.

arXiv

SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data

Wael AbdAlmageed

In many reasoning problems, the premises are not observed as discrete symbols, but must be inferred from high-dimensional inputs. Further, the predicate vocabulary, argument structure, and trusted evidence are supplied by a Knowledge Graph (KG), or rule definitions. Classical neuro-symbolic pipelines have a discrete interface between perception and deduction. We present a neuro-soft-symbolic architecture for differentiable deductive reasoning over latent perceptual facts and knowledge-provided predicates. SoftReason removes the gradient gap by representing the deductive state as a local soft interpretation tensor over candidate constants and predicates. Perception proposes probabilistic base facts, KG triples enter as high-confidence soft evidence, and every query anchor, predicate choice, and closure update remains differentiable. Our core innovation is a learned differentiable lift of the immediate-consequence operator. It uses predicate-definition embeddings and latent composition channels to form soft body-predicate mixtures, aggregate over all possible witnesses, propose query-conditioned head facts, and update the interpretation through a monotone probabilistic OR. We instantiate the framework on Knowledge-aware Visual Question Answering (KVQA), and demonstrates how SoftReason supports end-to-end perceptual grounding, KG evidence injection, and differentiable deductive closure in one trainable architecture.

arXiv

ProbSPARQL: Querying Knowledge Graphs with Multi-dimensional, Uncertain Numeric Data

Jingcheng Wu, Ratan Bahadur Thapa, Daniel Hernandez, Hongkuan Zhou, Steffen Staab

The SFB 1574 Circular Factory is building a shared knowledge graph infrastructure for integrating data about returned products. A central challenge is that circular-factory data include numeric measurements that (i) originate from sensors or are derived from sensor-based measurements, (ii) are frequently multi-dimensional, and (iii) are inherently uncertain, while downstream triage, validation, reliability-modeling, and reassembly-planning modules require queryable uncertainty representations. Current RDF and SPARQL technologies lack native support for harmonized querying and analysis of such uncertain numeric measurement data. To address this gap, we present ProbSPARQL, an upward-compatible SPARQL extension developed as an early-stage query-layer pilot for this infrastructure. ProbSPARQL models uncertain numeric values as random variables whose distributions are encoded by probabilistic RDF literal datatypes, and supports distribution-aware expressions, probabilistic filters, and divergence-based joins. We implement ProbSPARQL on Apache Jena ARQ and expose it through a Fuseki-compatible execution layer. We assess real-data applicability using project-derived measurement fragments covering GMM-encoded uncertainty and histogram-based empirical roughness distributions, and evaluate scalability separately on controlled ontology-conformant benchmarks with up to 5,000 angle-grinder instances and 1.5M triples. The results show feasible in-engine execution, filter-pushdown speedups over application-layer post-processing, and latency-accuracy trade-offs among divergence-join decision strategies.

arXiv

Digital Fragmentation and Generative AI Use Across 103 Million Application Events

Sumer S. Vaid, Ashley V. Whillans

Knowledge workers switch between applications thousands of times per day, spending nearly a tenth of the work year transitioning between digital applications in a process called digital fragmentation. Whether this fragmentation reflects who an employee is, where they work, or what kind of day they are having, has remained an open question. We analyzed 103 million application events recorded second-by-second from 1,017 employees across eight organizations that largely employ knowledge workers (e.g., law, financial services). Day-to-day variation in fragmentation within individual employees accounted for 44.6% of the variation in digital fragmentation, slightly exceeding stable individual differences between employees (35.8%), and far exceeding variation between organizations (19.6%). Fragmentation rose over the work week and reset after weekends and holidays. Higher-than-typical use of communication applications coincided with more fragmented work. Generative AI use also occurred on more fragmented days, but the period following AI use was marked by narrower, longer, and more predictable application use. These findings identify the workday as a key level for understanding and intervening on digital fragmentation and suggest that AI may help structure fragmented work rather than merely intensify it.

arXiv

Can LLMs Rank? A Tale of Triads and Triage

Gaurab Pokharel, Shafkat Farabi, Patrick J. Fowler, Sanmay Das

From housing allocation for households experiencing homelessness to triage in emergency departments, LLMs are increasingly being considered as judges of consequential decisions that require ranking people for scarce resources. Ranking large groups simultaneously is cognitively demanding and error-prone. A natural solution, drawing on decades of social choice theory, elicits pairwise comparisons and aggregates them into a total order. However, a fundamental question remains when LLMs serve as the pairwise judge: how can a practitioner tell, before committing to a ranking, whether the LLM's judgments are sufficiently consistent to trust the result? We discuss two different ways of identifying consistency. A classical diagnostic, the coefficient of consistency $ζ$, originally developed to measure judge reliability by counting circular triads in tournament graphs, provides a cheap, model-free measure of intra-run consistency. Various standard measures of distance between rankings, for example Kendall's $τ$, can measure inter-run variability. We show, in both theory and practice, that these measures are independently valuable, and advocate for using both to assess reliability of rankings. We demonstrate the practical importance of our results across two high-stakes prioritization tasks: homelessness service allocation and emergency department triage. Three different leading LLMs have considerably different performance profiles across these two axes of consistency. We provide guidelines for how practitioners could think about measuring and assessing consistency before committing to a model for ranking or prioritization.

arXiv

OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative Driving

Juntong Peng, Juanwu Lu, Yupeng Zhou, Can Cui, Yaobin Chen, Ziran Wang

We present OmniV2X, a generative foundation model for vehicle-to-everything (V2X) cooperative driving. The model directly interprets independent context sequences comprising multi-modal and multi-agent observations. The new design mitigates the computational cost of dense 3D perception, the vulnerability to data scarcity in cooperative scenarios, and the poor compliance with standardized messaging in existing methods that fuse multi-modal inputs into a shared representation. For training, we present an end-to-end supervised pipeline using a downstream trajectory generation loss, in which a high-capacity generative sequence planner implicitly learns to steer the model and leverage multi-modal inputs via cross-attention injection. As a foundation model, we demonstrate that OmniV2X pre-trained on large-scale single-agent planning datasets can efficiently adapt to cooperative environments by integrating the conditioning context with lightweight, standard-compliant V2X tokens. Evaluated on the DAIR-V2X-Seq dataset, OmniV2X outperforms existing end-to-end cooperative driving baselines, achieving state-of-the-art performance with less than 10% of the fine-tune V2X dataset and less than 1% of the communication bandwidth. We conduct comprehensive evaluations to demonstrate its computational efficiency and robustness under real-world constraints.

arXiv

Selective Cross-View Consistency for World Action Models: Held-Out Viewpoint Robustness Without Test-Time Camera Information

Bingqi Huang, Bingchuan Wei, Yingkai Cai, Zhaokui Wang

World action models (WAMs) jointly denoise future video frames and robot actions, and the video prior is expected to generalize their control. Camera viewpoint change remains one of their hardest perturbation axes. We study a question specific to this model class: when training with same-state cross-view image pairs, on which output coordinates should a consistency loss be imposed? The WAM denoising target mixes view-covariant coordinates, namely the predicted future scene, with view-invariant coordinates, namely the action chunk, future proprioception, and value. We show that consistency applied to the covariant block is provably harmful, shrinking legitimate view-specific content to a fraction $1/(1+4λ)$ of its true value, and we verify this shrinkage law in controlled experiments. Selective cross-view consistency (SCVC) therefore constrains only the invariant block, requires no camera labels, extrinsics, depth, or view synthesis at training or test time, and leaves the deployment interface unchanged. We introduce a carve-and-hold-out evaluation protocol on the LIBERO-Plus camera track that separates a distribution-matched ceiling from genuine interpolation and extrapolation to held-out viewpoints, with a matched pair-trained control isolating the effect of the consistency term from pair exposure. On held-out orbital viewpoints beyond the training envelope, SCVC improves closed-loop success over the matched control by 12.2 points (95% CI [7.4, 17.0]; +15.5, CI [11.7, 19.4], under an independent second seed) -- an effect two further camera axes replicate -- while interpolation within the envelope shows no gain in either seed (-1.2 and -4.3 points) and in-distribution competence is preserved (-0.6, -0.2). We also report a cross-backbone audit showing that published camera-robustness numbers are confounded by wrist-camera pose stability.

arXiv

Human agency in initial human-AI proof formalization workflows

Katherine M. Collins, Simon Frieder, Jonas Bayer, Jacob Loader, Jeck Lim, Peiyang Song, Fabian Zaiser, Lexin Zhou, Shanda Li, Sam Looi, Joshua B. Tenenbaum, Umang Bhatt, Adrian Weller, Jose Hernandez-Orallo, Cameron E. Freer, Valerie Chen, Ilia Sucholutsky

For centuries, human mathematicians have written proofs to substantiate their mathematical arguments; yet, the ability to automatically verify the validity of proofs has long been a challenge. Advances in AI systems' ability to generate code and engage in increasingly high-level mathematical reasoning promise to transform people's ability to formalize and thereby verify proofs. While many works focus on benchmarking the current frontier, we instead study how people use these tools and apply agency in doing so. We conduct a mixed-methods analysis into the initial impact of AI on people's formalization workflows: what people claim they want, what they see as the barriers to those visions, and how they actually use and adapt AI in practice. A qualitative survey reveals that people's preferences are diverse, but with a general desire for AI assistance in formalization that preserves high-level human control and agency over the proof discovery process. To assess how people actually engage with AI for formalization, we conduct a controlled user study in which participants formalize informal math problems and their proofs, with and without AI, across a range of mathematical problems at varying levels of difficulty and domains. Despite limitations of the tools at the time for autoformalization, participants tended to attain higher formalization accuracy when allowed access to AI tools than when formalizing on their own, with most participants flexibly choosing to use multiple different AI tools. Taken together, our work sheds light on the early stages of AI integration into formalization workflows, involving an intimate interplay of human agency and AI engagement.

arXiv

AIVV: Neuro-Symbolic LLM Agent-Integrated Verification and Validation for Trustworthy Autonomous Systems

Jiyong Kwon, Ujin Jeon, Sooji Lee, Guang Lin

Deep learning models excel at detecting anomaly patterns in normal data. However, they do not provide a direct solution for anomaly classification and scalability across diverse control systems, frequently failing to distinguish genuine faults from nuisance faults caused by noise or the control system's large transient response. Consequently, because algorithmic fault validation remains unscalable, full Verification and Validation (V\&V) operations are still managed by Human-in-the-Loop (HITL) analysis, resulting in an unsustainable manual workload. To automate this essential oversight, we propose Agent-Integrated Verification and Validation (AIVV), a hybrid framework that deploys Large Language Models (LLMs) as a deliberative outer loop. Because rigorous system verification strictly depends on accurate validation, AIVV escalates mathematically flagged anomalies to a role-specialized LLM council. The council agents perform collaborative validation by semantically validating nuisance and true failures based on natural-language (NL) requirements to secure a high-fidelity system-verification baseline. Building on this foundation, the council then performs system verification by assessing post-fault responses against NL operational tolerances, ultimately generating actionable V\&V artifacts, such as gain-tuning proposals. Experiments on a time-series simulator for Unmanned Underwater Vehicles (UUVs) demonstrate that AIVV successfully digitizes the HITL V\&V process, overcoming the limitations of rule-based fault classification and offering a scalable blueprint for LLM-mediated oversight in time-series data domains.

arXiv

Self-Routing: Parameter-Free Expert Routing from Hidden States

Jama Hussein Mohamud, Drew Wagner, Mirco Ravanelli

Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely on a learned router to map hidden states to expert assignments. In this work, we ask whether a dedicated learned router is strictly necessary for MoE routing. We propose Self-Routing, a parameter-free routing mechanism that uses a designated subspace of the token hidden state directly as expert logits, eliminating the router projection entirely while leaving the rest of the MoE layer unchanged. We evaluate Self-Routing on language modeling across different expert counts and model scales, and on ImageNet-1K classification by comparing it against a standard learned router, random-routing baselines, and dense non-MoE baselines. Our results show that Self-Routing remains competitive with the learned-router baseline while removing all dedicated routing parameters, and yields more balanced expert utilization, with about 17\% higher average normalized routing entropy and no explicit load-balancing loss. On ImageNet-1K with DeiT-S/16, Self-Routing also slightly improves over the corresponding learned-router MoE. These findings suggest that effective MoE routing can emerge from the hidden representation itself without requiring a separate learned router module.

arXiv

El Agente Gráfico: A Semantic Execution Runtime for Scientific Agents

Jiaru Bai, Abdulrahman Aldossary, Thomas Swanick, Marcel Müller, Yeonghun Kang, Changhyeok Choi, Naruki Yoshikawa, Zijian Zhang, Jin Won Lee, Tsz Wai Ko, Aiwei Yin, Mohammad Ghazi Vakili, Chris Crebolder, Varinia Bernales, Alán Aspuru-Guzik

Large language models (LLMs) can plan scientific workflows and generate code, but these capabilities do not specify how scientific state is validated, transferred and recorded across heterogeneous computational and experimental operations. Here we present El Agente Gráfico, a semantic execution runtime for scientific agents that uses typed execution graphs to enforce admissible scientific state transitions, record provenance and confine model judgement to explicit decision points. Using the same top-level LLM and task-specific rubrics on six university-level quantum chemistry exercises, El Agente Gráfico improved performance while reducing model cost by approximately 80% and wall-clock time by more than fourfold relative to our previous multi-agent architecture. Across ensemble spectroscopy and metal-organic framework (MOF) design, the runtime supported typed-state transfer, parallel execution and cross-session persistence. Open-ended studies of a disulfide redox mechanism and the vibrational hypothesis of olfaction required the agent to define the chemical scope and computational pathway of each investigation. A graph-construction skill distilled from these studies then enabled coding agents to author typed execution graphs for MOF literature mining. Together, these results show how typed execution graphs turn reusable procedural knowledge into scientific protocols that can be inspected, revised and transferred across computational and physical systems.

arXiv

Classical $\mathrm{SU}(2)$ Models Match or Exceed Shallow Variational Quantum Circuits on Vision Benchmarks

Christopher Fulton, Irene Tsapara, Lawrence Fulton

Quaternion-valued neural networks and variational quantum circuits (VQCs) both derive local transformations from $\mathrm{SU}(2)$ geometry, yet their performance on classical supervised learning remains poorly understood. We compare real-valued, quaternion-valued, and quantum classification heads on identical frozen features across MNIST, FashionMNIST, and CIFAR-10. CIFAR-10 uses a learned 16-dimensional bottleneck and frozen ImageNet-pretrained ResNet18 features to separate architecture from representation quality. Quaternion classifiers match or approach real-valued baselines while outperforming shallow VQCs. On MNIST and FashionMNIST, quaternion networks nearly equal real-valued MLPs, whereas product-state VQCs show lower accuracy and higher cost. On CIFAR-10, quaternion networks retain 94--97% of real-valued performance and remain stable under a 32-fold increase in dimensionality. Product-state circuits underperform quaternion classifiers, while entanglement gives modest grayscale gains but reverses under pretrained CNN features (9.25 pp degradation vs.\ product-state). Fubini--Study/QFI natural gradients improve geometric alignment but not short-horizon loss reduction vs.\ Adam. A Friedman test on five-seed MNIST detects model differences ($χ^2=12.796$, $p=0.0051$, $n=5$), with Wilcoxon tests yielding large effect sizes ($d>5$) for QuatNet vs.\ quantum comparisons. For FashionMNIST and CIFAR-10, large effects ($d>2.0$) are the primary statistic given $n=3$. These results indicate that quaternion networks provide efficient, stable $\mathrm{SU}(2)$ alternatives to shallow VQCs on tasks lacking intrinsic quantum structure. Shared local $\mathrm{SU}(2)$ geometry and shallow entanglement are insufficient, within the regime studied, to confer practical quantum advantage. Conclusions are limited to shallow, measurement-limited circuits on such tasks.

arXiv

Preserving Item Semantics for Free: Rethinking Token Initialization in LLM-Based Generative Recommendation

Donald Loveland, Liam Collins, Bhuvesh Kumar, Danai Koutra, Neil Shah

Recent advances in generative recommendation (GR) leverage large language models (LLMs) as recommender backbones, enabling LLMs to directly generate recommendations conditioned on item-interaction histories. In these systems, items are often represented through semantic IDs (SIDs) added to the LLM vocabulary as special tokens. Ideally, SIDs imbue item token representations with semantic priors, thereby improving model generalization. However, standard vocabulary expansion typically initializes these tokens as random Gaussian vectors, discarding the SIDs' underlying continuous geometry and forcing the LLM to relearn token relationships from interaction data. To demonstrate the consequences of this design, we first show that training from this initialization tends to organize SID embeddings around item popularity rather than semantics. We further show that, despite partially reducing the reliance on popularity and improving cold item performance, the computationally expensive process of continual pretraining (CPT) fails to reliably recover the original semantic geometry. To address these findings, we propose a simple, parameter-free intervention that initializes SID token embeddings directly from their corresponding centroids in the semantic embedding space. Requiring only a few lines of code and no additional training or inference overhead, this drop-in approach improves pure-SFT Recall@5 by up to 16%, reaches peak performance with up to 40% fewer SFT steps, and improves cold-item Recall@5 by up to 60%. Moreover, on datasets that benefit from additional CPT, centroid initialization reaches comparable performance while requiring half as many CPT epochs. Together, our findings show that preserving SID geometry, beyond shared-prefix structure, provides a simple and effective semantic prior for LLM-based GR.

arXiv

Shape Mutating Expert Compression:LorExperts and BTExperts

Inesh Chakrabarti, Sourjya Roy, Bowen Bao, Thiago Crepaldi, Spandan Tiwari, Ashish Sirasao

Mixture-of-Experts (MoE) language models deliver high capacity at low per-token compute, but deploying them cheaply requires compressing their many expert weight matrices. Expert pruning (e.g., REAP) and merging reduce cost but sacrifice accuracy and require retraining the router; low-rank delta decomposition of experts (e.g., D^2-MoE) preserves all experts and the router, but degrades sharply as the expert count grows because a single shared component cannot approximate many near-orthogonal experts. Because MoE expert weights are near-orthogonal, a single shared component (as in prior delta decomposition) scales poorly with the expert count; we show that experts nonetheless organize into functional co-activation communities that are decoupled from weight similarity. Building on this, we introduce LorExperts, a router-preserving compression method that clusters experts, keeps one full-precision dominant per cluster, and represents the remaining members as low-rank corrections to their local dominant. LorExperts retains all experts and the original router (no router retraining). At ~50% expert compression on Qwen3-30B-A3B and Gemma-4-26B-A4B, LorExperts preserves downstream accuracy and perplexity better than the baselines on most of the tasks; the margin over D^2-MoE grows with expert count E. We further give a reconstruction fine-tuning procedure for LorExperts, and BTExperts, a tree organization of dominants and corrections that enables inference-time amortization of shared computation.

arXiv

Conformal Calibration for Multi-Modal Regression with Missing Modalities

Ilia Azizi

Prediction intervals for multi-modal regression with tabular variables, text, images, or other input sources are difficult to calibrate when those sources disagree or one is missing. A single global quantile averages these regimes together instead of calibrating to the modality pattern observed at test time. We address this through a modality-aware conformal calibration layer. The layer trains or reuses one predictor per modality, computes a disagreement score from their predictions, and uses that score in split conformal calibration under a strict split protocol. We use the score in two complementary ways. First, a continuous disagreement-scaled method reallocates interval width across examples while preserving the usual marginal split-conformal guarantee. Second, a Mondrian (stratified) method calibrates within groups defined by disagreement or modality availability fixed before calibration, giving group guarantees under joint exchangeability of the calibration and test examples. Across four multi-modal datasets, the disagreement-scaled layer matches or improves the marginal conformal baseline in 59 of 60 paired runs for interval continuous ranked probability score (CRPS) and in 52 of 60 for interval width, while keeping empirical coverage near the 95% target. In stress tests with missing modalities, mask-matched recalibration recovers up to 19.5 percentage points of coverage in the hardest fixed-mask regime. The result is a simple, model-agnostic reliability layer for multi-modal regression systems. A project page is available at https://unco3892.github.io/modality-aware-conformal.

arXiv

Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space

Yiwei Chen, Bingqi Shang, Sijia Liu

Open-weight large language models (LLMs) are increasingly developed through complex, multi-stage pipelines, leading to intricate lineage relationships that reflect model origin, ownership, and evolution. Understanding these relationships is important for model provenance, governance, and supply-chain integrity. In this work, we investigate the notion of LLM "biometrics" (analogous to human biometrics) to ask whether LLMs exhibit intrinsic fingerprints in weight space alone, without access to input data, that reveal their origin and lineage. We formulate this as a lineage discrimination problem, distinguishing among independent-origin, same-series, and shared-base models. To characterize these relationships, we propose a unified geometric fingerprinting framework that analyzes weight matrices from two complementary perspectives: (i) spectral energy, captured by singular value distributions to encode global magnitude patterns, and (ii) subspace alignment, quantified via subspace deviations to capture directional geometry. Our analysis uncovers a clear hierarchy of structural similarity in weight space: spectral energy reliably distinguishes independently trained models and different model families, while subspace alignment enables fine-grained discrimination among closely related models, including variations in dataset scale and post-training procedures. Extensive experiments on over 110 diverse open-weight LLM pairs demonstrate that weight-space geometry provides a robust and interpretable signal for model lineage, enabling coarse-grained regime separation and fine-grained discrimination within shared-base models.

arXiv

The Sample Complexity of Policy Learning with Mu-Resets

Gene Li

We study policy-based reinforcement learning under the $μ$-resets interaction protocol of Kakade and Langford [KL02]. This interaction protocol enables the learner to sample trajectories from a given exploratory reset distribution $μ$, in addition to the starting distribution. We resolve the question raised by [KLS25] on the role of policy realizability for the sample complexity of this problem. Critically, the dependence on horizon $H$ is governed by the notion of coverage assumed of the reset distribution. Under bounded all-policy concentrability, we show a $\exp(Ω(H))$ sample complexity lower bound; with bounded pushforward concentrability, we show the dependence on horizon is tightly characterized as $\exp(Θ(\sqrt H))$.

Keep browsing

More papers from top AI conferences

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