Artificial Intelligence · Cross-listed from cs.CV
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Jiarui Chen, Zeqiang Lai, Jiangshan Wang et al. (+5 more)
Sparse
attention is a primary approach to reducing the latency of
diffusion transformers in long-sequence generation tasks, such as
video and high-resolution 3D asset generation. However, existing methods can degrade generation quality and fidelity at high sparsity levels. Through controlled oracle comparisons, we trace this degradation to three sources: constraints imposed by
token grouping, inaccurate interaction selection, and the
attention contributions lost when
tokens are discarded. Guided by this analysis, we propose Meta-Cached Sparse
Attention (MC-Sparse), a training-free framework that selects individual key-value (KV)
tokens while organizing similar queries into tile-aligned groups for efficient GPU execution. MC-Sparse caches metadata comprising query groups, KV indices selected using exact
attention probabilities, and residuals between dense and sparse
attention outputs, and reuses them across subsequent denoising steps. Across
video and 3D generation models, MC-Sparse achieves higher fidelity to dense-
attention outputs and larger denoising speedups than existing sparse-
attention baselines, without visible quality degradation. Relative to dense
attention, it delivers a $1.80\times$ denoising speedup on Minimax-H3-Base and a $2.32\times$ speedup on 3D asset generation, both with negligible quality loss.
Read the full abstract ▾
All authors Jiarui Chen, Zeqiang Lai, Jiangshan Wang, Ziheng Ouyang, Ye Huang, Xiangyu Yue, Cewu Lu, Chunchao Guo
Artificial Intelligence
Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification
Je Yang, Ivan Lobov and Thomas Karpati
The unprecedented computational scale of modern artificial intelligence depends on complex, multi-billion-transistor Systems-on-Chip, yet the workflows that verify these chips remain stubbornly manual. Although Large
Language Models (LLMs) have made rapid inroads into Electronic Design Automation (EDA), approximately 74.6% of existing studies target static Register-Transfer Level (RTL) code generation, leaving post-simulation verification and interactive waveform debugging largely untouched. We introduce Back-to-the-Future (BTTF), an end-to-end agentic framework that closes this infrastructural gap. BTTF distills massive, unstructured simulation dumps into a normalized relational SQLite database and couples it with a collaborative multi-
agent orchestration engine that translates natural-
language verification queries into schema-aware SQL while correlating signal anomalies with versioned RTL repositories. Across a 150-query
benchmark, BTTF attains 95.33% execution accuracy, charting a practical path toward autonomous EDA verification.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
IdeaLens: Detecting AI Ideas in Long-form Writing
Rishanth Rajendhran, Minjoon Choi, Jenna Russell et al. (+5 more)
While modern AI detectors identify who wrote the words, emerging policies on AI use increasingly hinge on a different question: who came up with the ideas? We introduce IdeaLens, a detector that identifies whether a document's ideas came from a human or AI (idea provenance), regardless of who wrote its words. To focus IdeaLens on ideas rather than prose, we represent documents as outlines: lists of items that each pair a discourse role with a brief, paraphrased description of the content, minimizing word-level overlap with the raw text. We train IdeaLens on 1M FineWeb documents with silver labels from Pangram, a prose provenance detector. Since the outlines are largely stripped of surface-level information, the labels must be fit mainly through the ideas. In a controlled study, IdeaLens's AI flag rate drops from 95% to 7% as models write from increasingly detailed human plans, while Pangram 4 still flags 92%; from AI-derived plans, IdeaLens stays above 96%. Conversely, on a new
dataset of 50 stories that human authors wrote from AI-generated plans, IdeaLens flags 68% of the stories as AI, compared to 8% for Pangram 4. On a comprehensive suite of 19 existing detection
benchmarks, we show that IdeaLens maintains strong detection rates at low false positive rates, suggesting that ideas themselves provide a powerful discriminative signal, and its performance holds across domains, formats, and
languages. Finally, we examine 90K predictions from IdeaLens to characterize systematic differences between human and AI ideation. We release our models and labeled
datasets to facilitate future research on idea provenance detection.
Read the full abstract ▾
All authors Rishanth Rajendhran, Minjoon Choi, Jenna Russell, Ramya Namuduri, Deniz Bölöni-Turgut, Marzena Karpinska, John Wieting, Mohit Iyyer
Artificial Intelligence
Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation
Guangyuan Dong, Ziwei Hong, Xuehao Zhou et al. (+6 more)
Medical question answering spans specialties and clinical operations that may benefit from different adaptation directions. We propose ARBOR, a parameter-efficient method that selects rank-one components from a shared low-rank basis for each question. An additive gate combines question representations, specialty tags, operation tags, and their interaction; a learned coefficient scales the adapter residual. An illustrative separation under orthogonal, equiprobable subtasks shows how conditional selection can avoid an approximation floor faced by a fixed update with the same active rank. This result motivates the design without asserting a corresponding bound for medical corpora. On Qwen3-8B across CMB, CMExam, MedQA, and MedMCQA, five-seed experiments yield 69.69% mean accuracy across
benchmarks, exceeding LoRA r16 and MoELoRA by 1.26 and 1.30 percentage points, respectively. The reported advantage over LoRA r16 increases from 0.08 to 1.94 points as training expands from one to seven specialties. Tag perturbations and atom masking support the usefulness of clinical routing, while atom clusters align with the supplied specialty labels (adjusted Rand index 0.62). Calibration, transfer, and measured costs further characterize the method. These findings support structured conditional adaptation for medical QA, while leaving clinical safety and broader deployment untested.
Read the full abstract ▾
All authors Guangyuan Dong, Ziwei Hong, Xuehao Zhou, Zidong Yu, Bingchen Liu, Kehan Liu, Chuang Liu, Rong Fu, Yuchao Hou
Artificial Intelligence · Cross-listed from cs.LG
MatrixFormer: A Foundation Model for Matrix Completion
Dwaipayan Saha, Jacob Feitelberg, Kyuseong Choi et al. (+2 more)
Matrix completion underlies problems from tabular imputation to causal inference, yet existing tabular foundation models treat it as entry-by-entry prediction, repeating context for every target and discarding the
matrix's two-dimensional structure. We introduce MatrixFormer, a pre-trained
matrix-native
transformer that predicts a full distribution for every missing entry in a single forward pass. MatrixFormer is trained entirely on synthetic low-rank and latent-factor
matrices under diverse missingness patterns. Applied zero-shot and with the same model weights, MatrixFormer achieves competitive performance on causal inference panel-data tasks,
language-model
benchmark-score completion, tabular imputation, and recommendation systems
matrix completion. These results position MatrixFormer as a general-purpose foundation model for
matrix completion.
Read the full abstract ▾
All authors Dwaipayan Saha, Jacob Feitelberg, Kyuseong Choi, Raaz Dwivedi, Anish Agarwal
Artificial Intelligence · Cross-listed from cs.CL
Balancing Memory Pathways: Analyzing and Improving Memory Utilization in Hybrid LMs
Hyunji Lee, Joykirat Singh, Zaid Khan et al. (+5 more)
Recurrent-
attention hybrid
language models (LMs), which interleave
attention and recurrent layers, are increasingly used to combine the efficiency of the recurrent layers with the strong performance of
attention layers. Prior work suggests that
attention and recurrent layers offer complementary pathways to use past information:
attention supports precise
memory recall from earlier
tokens, while recurrent layers support consolidation of disparate information over long contexts. However, we observe that simply having access to both pathways does not mean that hybrid LMs are effectively using them. We find that they rely substantially more on
attention than on the recurrent state. Standard supervised fine-tuning improves overall performance but does not improve how the two
memory pathways are coordinated: the model becomes more reliant on information propagated by
attention layers, while its use of information propagated by recurrent layers remains limited. To encourage better coordination between the two
memory pathways, we add an auxiliary loss that limits
attention's access to earlier context while the recurrent state propagates through the full sequence. This objective encourages the model to retain and use information through the recurrent pathway alongside
attention. It improves overall performance, with particularly strong gains on tasks involving longer contexts or requiring information aggregation, consistent with the strengths of recurrent layers observed in analysis. Crucially, this imbalance and the benefit of our auxiliary loss generalize: they apply to multiple recurrent-
attention LMs in question-answering and agentic tasks, as well as to
attention-based LMs that combine different forms of
memory. Together, our findings show that simply providing multiple
memory pathways does not ensure their effective use, and that targeted supervision is needed to better coordinate them.
Read the full abstract ▾
All authors Hyunji Lee, Joykirat Singh, Zaid Khan, Justin Chih-Yao Chen, Elias Stengel-Eskin, Alessandro Sordoni, Arman Cohan, Mohit Bansal
Artificial Intelligence · Cross-listed from cs.MA
BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents
Ziyan Wang, Shuqing Shi, James Oldfield et al. (+5 more)
In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputation. Large
language model (LLM)
agents now act for users, raising risks to their money,
privacy, and reputation. We introduce BazaarBench, a simulated C2C marketplace and
benchmark for evaluating the safety of these
agents. It tracks ownership, item condition, and commitments across transactions, combining record checks with rubric-based LLM judgments to identify six failure types across five stages. We run three base
markets for 30 simulated days, each with 100
agents using one model and inventories drawn from a public eBay sample. Across 45 continuations, we evaluate five models under ordinary instructions, deadline pressure, or
adversarial instructions to exploit other traders. Each continuation runs for seven simulated days from a copy of a
market's day-30 state. The tested model controls the same 20 selected
agents, retaining their personas, inventories, and histories, while the other 80 keep the base model. All five models attempt to promise the same item to multiple buyers under ordinary instructions. Adding targets and deadlines increases these attempts for every model. Under
adversarial instructions, the share of tested sellers' committed transactions completed despite unavailable items or overstated conditions rises from 15.4% to 33.4%, reaching 55.5% for GPT-5.4. Averaged across models and
markets, simulated weekly earnings per tested
agent rise from USD 20 under ordinary instructions to USD 33 under
adversarial instructions. Most of the increase comes from items the sellers never held. We release the simulator, saved
market states, evaluation code, and records covering 357,608
agent model calls for evaluating new models and developing safer marketplace
agents.
Read the full abstract ▾
All authors Ziyan Wang, Shuqing Shi, James Oldfield, Samuele Marro, Jialin Yu, Philip Torr, Yali Du, Adel Bibi
Artificial Intelligence · Cross-listed from cs.LG
BRANCH-MoE: Balance-Aware Tree Routing for Large Embedding Models
Gang Fu, Adel Javanmard, MohammadHossein Bateni et al. (+1 more)
Mixture-of-experts (MoE) layers increase model capacity without a proportional increase in per-example computation. However, conventional flat routers can yield imbalanced expert utilization and treat experts as an unstructured collection, whose indices carry no topological meaning. We introduce BRANCH-MoE, a routing architecture that places \(E\) experts at the leaves of a binary decision tree of depth \(\log_2 E\). At each internal node the branching probability is centered on the arrival-weighted mean score of the traffic reaching that node. This mean is estimated using an exponential moving average, which promotes utilization of both child subtrees without an auxiliary load-balancing loss. We show that this moving-average estimate admits an explicit noise-lag trade-off. We prove that for linear node maps and log-concave arrival distributions, this mechanism prevents routing-mass collapse. We further establish that, under a frozen router, an expert's execution frequency controls its
stochastic-gradient convergence rate, and that confident decisions near the root bound cross-device communication when experts are assigned to devices by tree prefix. We evaluate BRANCH-MoE against Switch softmax, DeepSeek-V3 dynamic-bias, Skywork logit-normalized, and deterministic hash routing on Criteo click-through-rate prediction, Forest Covertype,
HIGGS, and YearPredictionMSD, using \(E=16\), top-\(4\) routing, and five random seeds. Our results show that hierarchical routing can preserve task quality and balanced utilization while inducing a
topology that supports localized expert co-activation and reduced communication.
Read the full abstract ▾
All authors Gang Fu, Adel Javanmard, MohammadHossein Bateni, Vahab Mirrokni
Artificial Intelligence · Cross-listed from cs.LG
Closing the Context Gap: Activation Alignment for Tabular In-Context Learning
Yoel Zeldes
Tabular foundation models perform in-context learning (ICL) by conditioning predictions on labeled training examples provided as context. Unlike traditional models that separate training from inference, these models must process all training examples in every forward pass, making each prediction expensive. Restricting the number of training examples reduces this cost but substantially degrades performance. Instead of discarding context, we propose activation
alignment, a method that leverages the full context to teach a model how to behave when seeing only a subset. This is achieved by training a lightweight linear transformation on synthetic unlabeled data to map the intermediate activations of a data-constrained "student" (using partial context) toward those of a full-context "teacher" (using all data). Training the aligner requires no GPU and converges in seconds to minutes on commodity hardware. We evaluate on 38 classification
datasets from the TabArena
benchmark using the leading two tabular foundation models, TabPFN-3 and TabFM. Across all context budgets, the aligned student yields broad, statistically significant improvements over the unaligned baseline for both models. In low-data regimes,
alignment recovers nearly half of the teacher's predictive advantage. The method provides a practical, low-overhead approach to achieving the inference speed of compact contexts while closing a significant fraction of the performance gap to the full-context teacher.
Read the full abstract ▾
Artificial Intelligence
The Pushback Paradox: A Two-Probe Diagnostic for Language Model Compliance
Stefan Bühler, David Exler, Markus Reischl et al. (+1 more)
Are
language models compliant with user instructions? A model that always complies can be stopped but also exploited, while one that always resists can be neither exploited nor stopped. We contribute an open two-probe
benchmark that can place any
language model on this spectrum. In the active probe, a user instructs the model to act and accept a lower payoff, which measures exploitability. In the passive probe, the user instructs it to wait and give up a higher payoff, which measures stoppability. The two compliance rates combine into a compliance index $\kappa$. Applied to twelve
language models, the
benchmark shows that seven mostly follow the instruction in both probes and justify their action by pointing to the instruction. Only Claude Sonnet-4.6 and Claude Opus-4.7 can be stopped without being exploitable, Claude Opus-4.6 and GPT-5-mini resist both instructions, and no model is exploitable but unstoppable. Knowing where a
language model sits on the compliance index $\kappa$ matters for human operators and for multi-
agent systems, whether distributed or orchestrated.
Read the full abstract ▾
All authors Stefan Bühler, David Exler, Markus Reischl, Mark Schutera
Artificial Intelligence · Cross-listed from cs.CV
VideoTapestry: Query-Adaptive Memory Refinement for Multi-Agent Long-Video Understanding
Yucheng Liu, Yufei Yin, Mingxiao Feng et al. (+3 more)
Long-
video understanding places substantial demands on
memory, as answering questions often requires retrieving information distributed across extended temporal spans. Existing approaches broadly follow two paradigms: query-driven exploration, which is sensitive to localization errors, and query-independent
memory construction, which may omit question-specific details. We introduce VideoTapestry, a training-free multi-
agent framework that adapts a preconstructed hierarchical
video memory through coarse-to-fine, query-driven refinement. The preconstructed
memory organizes
video content into three levels, capturing global narrative context, event-level temporal structure, and fine-grained relational evidence, respectively. To support coarse-to-fine localization and observation, we assign a specialized
agent to each level, keeping
retrieval and refinement within a scale-specific context. Guided by the query, these
agents revisit relevant
video regions and enrich layer-wise
memories with targeted
multimodal observations. Their refinements are assembled according to the original hierarchy into a composite query-adaptive
memory, preserving global context in a compact form while retaining fine-grained evidence along query-relevant branches for final
reasoning. Compared with direct GPT-5.5 inference, VideoTapestry achieves absolute accuracy gains of 17.2%, 14.9%, 9.8%, and 7.0% on LVBench, LongVideoBench (Long),
Video-MME (Long), and EgoSchema, respectively, achieving the state-of-the-art results among all competitors.
Read the full abstract ▾
All authors Yucheng Liu, Yufei Yin, Mingxiao Feng, Jiajun Deng, Wengang Zhou, Houqiang Li
Artificial Intelligence
Language models can notice an impossible engineering problem yet still report it as solved
Shaoliang Yang and Jun Wang
Language models draft engineering calculations, but answer accuracy does not show whether they reject an impossible problem. We tested 14 models on 30 pairs of mechanics problems, each with a valid version and one made impossible by changing a given value or assumption. Two independent solvers verified every answer key and showed that each flawed problem was physically impossible. We scored solving of valid problems separately from rejection of their flawed counterparts. Each reply required a "solved" or "cannot solve" status; rejection meant "cannot solve" or withholding an answer. The initial
prompts did not warn that problems could be flawed. Across three recent models, 12 of 90 replies failed to reject a flawed problem. In 11 of these replies, the model stated the flaw, answered a corrected problem and still reported the original as "solved", according to artificial intelligence raters and numerical checks. We later retested four models from one provider, offering "flawed" instead of "cannot solve" and asking them to name and explain the defect. Three models showed statistically significant increases in rejection, but valid-problem solving fell in three. Evaluations therefore need to score both versions and distinguish flaw recognition from the reported status.
Read the full abstract ▾
Artificial Intelligence
Collective intelligence through aggregation
Franz Dietrich and Christian List
Suppose a committee, expert panel, or other group is making judgments on some issues, where these may be not just yes/no-questions, such as whether a defendant is guilty, but also variables with many possible values, such as macroeconomic or meteorological variables or travel directions. Furthermore, there may be interconnections between different issues, as in the case of economic or
climate variables. How can the group arrive at "intelligent" collective judgments, based on the group members' individual judgments? We investigate three challenges raised by this judgment-aggregation problem. First, reasonable methods of aggregation (such as defining the collective judgment for each issue as the average or median judgment) can produce inconsistent collective judgments. Secondly, many methods of aggregation are manipulable by strategic voting. Finally, not all methods of aggregation are conducive to tracking the truth on the issues in question. We prove new impossibility or possibility
theorems on all three challenges, identifying what it takes to produce collective judgments in a consistent, non-manipulable, and truth-tracking manner and thereby to achieve collective intelligence through aggregation. Overall, the median method, though imperfect, performs reasonably well. We also note the relevance of our analysis for non-human group decisions.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
AffordCraft: Scalable Construction of Task-Ready Simulation Assets from Single Images
Haoyun Yang, Xueyang Zhou, Ziyi Xie et al. (+1 more)
Robot learning in simulation depends on the objects the simulator offers. Many tasks need objects with separate parts, joints that allow the required motion, and physical properties that remain valid under contact. Existing methods recover this structure anew for every image: generative models predict parts and joints that mostly fail to settle or move in simulation, and general-purpose
agents need a long session of model calls for each photograph. AffordCraft builds such an asset from a single RGB image and a task instruction by
retrieval instead of generation: it locates the object and the part to operate, selects a matching entry from a library of articulated assets, and fits it to the image while keeping its parts and joints intact. Without any box or mask marking the object, AffordCraft produces a physically valid asset for 1,703 of 2,000 photographs from 31 categories. Five generative methods pass on at most 45% of the same photographs and, at the median, need 10 to 78 times our GPU time per valid asset. On 50 cluttered images, 162 of 237 annotated objects pass the same physical test after automatic detection. Growing the library from 141 to 11,372 entries needs no change to the method and raises category coverage from 46% to 100% and the share of selections with the requested label from 18% to 51%. We also build manipulation tasks from the constructed assets, both with single objects and in composed scenes; policies trained on scripted demonstrations complete both kinds of tasks from initial states unseen in training.
Read the full abstract ▾
All authors Haoyun Yang, Xueyang Zhou, Ziyi Xie, Yongchao Chen
Artificial Intelligence · Cross-listed from cs.LG
Differentially Private Mixing of Public Datasets Improves Private Learning
Yufei Chen, Tejumade Afonja, Anvith Thudi et al. (+1 more)
Many machine learning applications involve sensitive data and therefore require training under differential
privacy (DP). However, DP training often degrades model utility. In some cases, first pre-training the model on "public" data before finetuning with DP on the sensitive data can reduce the drop in utility. However, the success of this depends on how relevant the selected public
dataset is to the sensitive data. We introduce the first pipeline that privately learns the mixture of several public
datasets to pretrain on for a given sensitive downstream task. Our key insight is that we can privately find the best mixture of multiple public
datasets by privately learning a low-dimensional linear model. We tested our method on the NIH
dataset for X-ray classification and the ENRON email
dataset for
language modeling. Applying our method to find tailored mixtures of X-ray
datasets to pretrain on for diseases in the NIH ChestX-ray14
dataset, we improved macro AUC by up to 0.037 across
privacy budgets compared to the baselines, with gains as large as +22.8% relative AUC on Cardiomegaly at $\epsilon=1$. For DP training on the ENRON
dataset, pre-training on our mixture of The Common Pile (a collection of public-domain text
datasets) decreased test perplexity by 16% relative to the baseline mixtures.
Read the full abstract ▾
All authors Yufei Chen, Tejumade Afonja, Anvith Thudi, Nicolas Papernot
Artificial Intelligence · Cross-listed from quant-ph
Large Language Model-Guided Discovery of Weight-Five Bivariate Bicycle Codes
Juan Cruz-Benito
Building on our earlier program-
evolution workflow guided by large
language models (LLMs), we study weight-five bivariate bicycle (BB) and perturbed bivariate bicycle (PBB) codes. The resulting catalogue contains 1,142 distinct code proposals, including 1,081 nonbaseline proposals attributable to LLM-generated programs. Across the catalogue, we certify connected Calderbank–Shor–Steane (CSS) realizations [[96,4,10]], [[140,6,10]], and [[180,4,14]]. A post-search comparison certifies seven imported Lin–Pryadko archive constructions. For leading parameter triples also represented in that archive, we provide exact distance evidence, explicit bivariate presentations, and verified component reductions. A basis-independent connectivity analysis identifies 409 of the 1,142 catalogue entries as disconnected and shows that 73.1% of the classes with exact distance certificates contain repeated connected components. Algebraic analysis organizes the connected CSS classes into order-3, order-7, and order-15 cyclotomic-kernel strata. The strongest exact connected PBB parameter point is [[216,4,10]], attained by two distinct component classes. Among the 936 distinct CSS proposals from the LLM-guided campaign with a recorded positive distance, 816 (87.18%) are certified at $d\geq5$. For comparison, three random-search controls each sample 6,444 CSS code proposals uniformly without replacement, using the same per-
lattice and encoded-dimension sample counts as the LLM-guided campaign. In these controls, 4,672–4,785 proposals (72.50–74.26%) meet the same criterion. The LLM-guided campaign has the higher certified yield, while the random controls cover more connected classes. Together, these results extend LLM-guided discovery to a more constrained code family and provide a reproducible structural and exact-distance account of its strongest candidates.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Frozen Factor or Spectral Band? Disentangling Two Choices in Low-Rank LoRA
Adnan Slimane Ali, Ayoub Belfatmi and David Ngwe Pouth
Spectral variants of low-rank adaptation (LoRA) choose both a subspace and which factor to freeze. We separate these choices by freezing the input factor A or output factor B on the top or bottom singular directions of pretrained weights, with learning rates selected separately. At rank 2, the same-band advantage of freezing A is larger than either within-factor band difference on all four task-model pairs with complete comparisons. Freezing B also trails comparable-budget free LoRA by 8-18 percentage points on five pairs spanning a formatting task and OpenBookQA. The A-frozen advantage persists in a single-GPU-model replication and within individual MLP module groups, including controls with equal or greater trainable counts for B frozen, and when A is frozen on a random orthonormal basis. The factor contrast weakens with rank. On OpenBookQA / Qwen2.5-1.5B at rank 16, PEFT's MiCA implementation trails comparable-budget LoRA by 3.08 points under a shared training recipe transferred from the MiCA paper. A trained oracle output subspace largely removes the low-rank deficit; partial warm-up gains recur across three direction seeds. The factor-versus-band ordering is descriptive; an approximate multiplicity audit weakens several earlier significance claims. These results extend known factor asymmetry by showing how its magnitude depends on spectral placement, rank and training conditions.
Read the full abstract ▾
Artificial Intelligence
FREA: A Multi-Source Expert Benchmark for Reaction Feasibility Verification
Botao Yu, Bo Zhou, Daniel Adu-Ampratwum et al. (+7 more)
As generative models and AI
agents propose chemical reactions at a scale beyond expert review, feasibility verifiers decide which proposals enter synthesis planning. But do their decisions agree with chemists across different kinds of candidates? We introduce FREA, a
benchmark of 751 reactions labeled by expert chemists under an explicit feasibility criterion, drawn from retrosynthesis model proposals, zero-yield experimental records, edits by large
language models (LLMs), and five negative candidate generation methods. Our evaluation finds that no verifier leads across all sources: LLMs given only the criterion are competitive with dedicated verifiers, while forward models perform best on retrosynthesis proposals but reject most feasible edits of recorded reactions at the evaluated operating points. Looking beyond aggregate scores, both forward models perform below chance when separating infeasible alternative disconnections from feasible generated candidates. To study whether negative supervision addresses these weaknesses, we also release a corpus of over 14 million recorded reactions and generated negative candidates. In matched training comparisons, adding a mixture of generated negatives to forward training raises mean AUROC across sources, but these gains do not extend to retrosynthesis proposals. Varying the generation method further shows that the largest gain on generated candidates coincides with worse proposal screening. These findings motivate evaluating verifiers against experts across sources and designing negatives for transfer to model proposals.
Read the full abstract ▾
All authors Botao Yu, Bo Zhou, Daniel Adu-Ampratwum, Frazier N. Baker, Ziru Chen, Reza Averly, Ye Liu, Wenhao Gao, Xia Ning, Huan Sun
Artificial Intelligence · Cross-listed from cs.CL
Word-Level Text Unmixing via Evidence-Preserving Ownership Routing with Language Models
Jinglin He, Siyang Jiang, Lixing He et al. (+2 more)
Text from multiple sources can become interleaved into a single sequence when attribution metadata is lost, such as overlapping
speech transcripts, document reading flows, or concurrent
agent streams. We formalize this challenge as Word-Level Text Unmixing: given an interleaved lexical stream and source count K, recover the original source sequences while preserving every word occurrence and its within-source order exactly. Directly generating separated texts with LLMs can omit, duplicate, or hallucinate words, violating this exact-reconstruction objective. We therefore propose Evidence-Preserving Ownership Routing (EPOR), which decouples source-ownership prediction from reconstruction. EPOR adapts a causal LLM to predict canonical ownership routes conditioned on the mixed stream and prior routing decisions. At inference, completion-safe constrained decoding is combined with deterministic indexed reconstruction, yielding structurally valid K-source partitions that preserve every observed occurrence exactly once. We also introduce UNMIXBENCH, covering controlled synthetic mixtures, timestamp-derived
speech from AMI and ICSI, layout-derived document streams from ReadingBank, and simulated concurrent digital outputs. Across five evaluation tracks, a 4B EPOR model achieves the lowest mean minimum-permutation word error rate among finetuned baselines, reducing the five-track mean by 22.3% relative to compact source-array generation and remaining competitive with zero-shot frontier LLMs. These results show that when lexical evidence is fully observed, separating ownership inference from lexical regeneration provides a reliable alternative to direct generation.
Read the full abstract ▾
All authors Jinglin He, Siyang Jiang, Lixing He, Guoliang Xing, Hongkai Chen
Artificial Intelligence · Cross-listed from cs.RO
SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models
Xiaodong Wang, Tianle Li, Chuanxin Song et al. (+4 more)
Action-conditioned
robot world models must respond precisely to
robot trajectories while preserving realistic visual dynamics, yet learning both from heterogeneous
robot videos remains challenging. Simulation offers structured motion supervision, but appearance differences hinder direct transfer, and inaccurate simulation predictions can misguide real-
video generation. We present SimForcing, a simulation-guided framework that uses simulation both as a source of transferable motion knowledge and as a controllable reference for prediction. First, we transfer motion knowledge from a simulation teacher through latent-motion
distillation, aligning temporal changes in latent space to internalize motion priors while mitigating the influence of appearance differences. Second, we introduce multi-block simulation conditioning with condition dropout to exploit predicted simulation trajectories without relying excessively on their accuracy. Our simulation-conditioning classifier-free guidance scheme unifies these two ideas by balancing predictions based on internalized motion knowledge with those additionally guided by simulation latents. The jointly trained student generates both simulation conditions and real-domain
videos, requiring no additional world model at inference. On Bridge, SimForcing achieves the best PSNR, SSIM, LPIPS, and FVD among the compared methods without external embodied pretraining. Evaluation on InternData-A1 further supports its applicability across
robot datasets. Moreover, using our trained world model to initialize a
vision-
language-action model improves LIBERO success, suggesting its utility for downstream policy learning. \url{https://github.com/Wang-Xiaodong1899/SimForcing}
Read the full abstract ▾
All authors Xiaodong Wang, Tianle Li, Chuanxin Song, Junliang Xie, Zhanmi Zhong, Suiying Wu, Peixi Peng
Artificial Intelligence
Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving
Jiaqi Zhao, Haodong Chen, Jitai Hao et al. (+4 more)
LLM
agents increasingly execute complex workflows involving multi-turn
reasoning, tool use, and parallel
agents. Efficient serving requires decisions that span two layers with complementary information: the
agent harness understands workflow dependencies, context lifecycles, and execution objectives, whereas the inference engine observes request queues, KV-cache state, resource pressure, and execution capabilities. Existing interfaces do not systematically connect these views, limiting workflow-aware execution. HEAR, a bidirectional Harness–Engine Pairing protocol for agentic LLM serving. HEAR standardizes how the harness communicates workflow intent and execution requirements and how the engine returns runtime state, capabilities, and outcomes. By separating protocol semantics from optimization policies, HEAR supports diverse coordination strategies without changing workflow or model semantics. We instantiate HEAR for online cache-aware runtime coordination and workload-aware execution-mode selection for
agent roles. Across four conversational and research-
agent benchmarks under
memory-constrained, concurrent serving, HEAR achieves a $1.61\times$ batch speedup and reduces median time-to-first-
token by $2.23\times$ on SCBench. Mooncake shows that workflow intent and live engine state provide complementary benefits across load regimes. On BrowseComp-Plus and DeepResearchBench, workload-specific configurations yield $1.23\times$ and $2.45\times$ end-to-end speedups, respectively, without observed task-quality degradation. These results establish HEAR as a reusable coordination substrate for efficient agentic LLM serving.
Read the full abstract ▾
All authors Jiaqi Zhao, Haodong Chen, Jitai Hao, Wei Zhao, Jinghao Pang, Qiang Huang, Jun Yu
Artificial Intelligence
The Review Lottery: Benchmarking an Observational Estimator of Peer-Review Noise (ICLR 2017-2025)
Feilian Huang
How much of a conference accept/reject decision would change if the same paper were reviewed by a different set of reviewers? Running a second independent program committee is the gold standard for answering this, but it is prohibitively expensive: done only twice (NeurIPS 2014 and 2021). We build an observational
estimator of this quantity from public review data alone, calibrate it twice, and apply it to nine years of ICLR (2017-2025; 36,113 papers, 134,912 reviews). The
estimator decomposes scores with a
Bayesian ordered-probit model into paper quality and reviewer noise, maps scores to decisions with a logistic model, and simulates two independent committees (posterior draws B=1,000; committee sizes k=2,3,4). Estimated disagreement rates are 23-30% at k=2 and 18-24% at k=4; 30-50% of accepted papers would be rejected. External calibration: at the NeurIPS 2021 reviewer-count caliber (k=3), the simulated 2021 disagreement rate is 23.3% [21.7%, 25.0%] vs. reported 23.0% (bias +0.3pp); accept precision and committee correlation agree within 5pp and 0.04. Internal calibration: on 18,740 papers with 4+ reviews, random model-free 2+2 reviewer splits agree with the k=2 simulation within 1pp in 2018 and 2021-2025. Longitudinally, we find no robust time trend in reviewer noise over 2017-2025. The high accepted-paper flip rates of 2020 and 2021 have distinct mechanisms: the 2020 four-point scale compressed scores (23.7% of papers had zero within-paper variance), and a counterfactual shows coarsening the scale raises disagreement by about 7pp; 2021 instead combined the lowest signal-to-noise ratio in the sample with the most threshold-crowded acceptances. For the LLM era, a 2023 breakpoint test on within-paper score variance finds no break, but the design has almost no power, and no post-2022 review text or confidence data exist, so no LLM attribution is attempted.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
Mind the Accent Gap: British Accent Robustness in Speech-Driven Financial Voice Assistants
Aadam Haq, Oggi Rudovic, Malcolm Chadwick et al. (+5 more)
AI voice assistants often use Automatic
Speech Recognition (ASR) with LLM-based
reasoning, yet existing systems struggle with regional British accents, including Scottish, Irish, and Welsh accents, since most ASR models are trained predominantly on American English voice data. Consequently, errors can carry through to the LLM stage, corrupting tool-call arguments and producing wrong or missing responses, which is especially costly in finance. Deployable ASR must also meet tight latency and
memory budgets, making an accent-robust model choice even harder. We introduce CavaBench, the first internally collected
benchmark of spoken financial queries, and use it to evaluate a range of ASR models and their end-to-end ASR-LLM pipeline behaviour across self-reported British accents. We find that WER strongly predicts downstream tool-calling accuracy ($r = -0.93$) but can fail to reflect task-level performance, with accent-related failures varying substantially across models and acoustic conditions. These findings guide the design of more inclusive, reliable voice-based financial assistants.
Read the full abstract ▾
All authors Aadam Haq, Oggi Rudovic, Malcolm Chadwick, Jay Rainey, Shucong Zhang, Ricardo Guerrero, Sourav Bhattacharya, Maja Pantic
Artificial Intelligence · Cross-listed from cs.CR
Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks
Tobias Heldt, Matt Turk, Christoph Landolt et al. (+1 more)
The release decision for frontier AI systems increasingly relies on cyber capability
benchmarks, yet public vulnerability
benchmarks can expose
agents to previously published advisories, exploits, and fixes, making it difficult to distinguish prior exposure from capability on unseen vulnerabilities. We evaluate open-weight and proprietary AI models on exploit generation, vulnerability repair and subsequent attacks in five nonpublic software environments, including vulnerabilities we privately disclosed while they remained unpatched. Researcher-developed and reviewed deterministic graders, not LLM judges, determine task scores. Comparisons with 209 disclosed vulnerabilities and cryptographic challenges reveal substantial variation across systems and vulnerability types. Repair scores exceed attack scores in two nonpublic environments and fall below them in three. Passing an initial security test is also insufficient: another exploit succeeds in 92 of 524 non-independent defender test intervals after the initial exploit is stopped. These results motivate vulnerability-specific attack-repair comparisons and subsequent resistance tests.
Read the full abstract ▾
All authors Tobias Heldt, Matt Turk, Christoph Landolt, Mario Fritz
Artificial Intelligence
Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control
Shengtao Wen, Xiang Chen, Yu Tian et al. (+3 more)
World-model controllers rely on action-conditioned dynamics for prediction and planning, yet real control systems often execute commands asynchronously due to communication delay, packet loss, reordering, and actuator buffering. We study how asynchronous execution changes the action semantics assumed within world-model controllers, rather than treating it only as an external control disturbance. Through controlled interventions, we identify two architecture-dependent failure modes: planning-based controllers such as TD-MPC2 suffer from a future-action timeline mismatch between imagined and executed action sequences, while recurrent world models such as DreamerV3 can attribute observed transitions to commands that were not actually applied. Our analysis shows that TD-MPC2 requires the correct future action sequence during latent dynamics rollout, whereas DreamerV3 requires timely attribution of each transition to the action that generated it. Based on these findings, we introduce two lightweight execution-consistent interfaces, Future-Sequence for TD-MPC2 and Applied-Action Feedback for DreamerV3, that correct these mismatches without modifying the pretrained world models. Experiments across delays, packet loss, reordering, multiple control domains, measured network traces, and a process-separated asynchronous stack consistently support both diagnoses and the corresponding architecture-specific corrections.
Read the full abstract ▾
All authors Shengtao Wen, Xiang Chen, Yu Tian, Lingbing Guo, Lina Gong, Sheng-Jun Huang
Artificial Intelligence
DGA-Muon: Decoupled Geometry-Aligned Adaptive Scaling for Muon
Wenpeng Zhang and Runsheng Yu
While NorMuon has achieved strong empirical performance in pretraining, its underlying adaptive mechanism remains largely heuristic and poorly understood. In this work, we provide the first systematic theoretical analysis of NorMuon's adaptivity, revealing that it primarily arises from orthogonalization-induced geometry rather than genuine optimization dynamics, serving to offset the resulting
geometric non-uniformity. Under exact orthogonalization, the adaptive scaling factors degenerate into a single global scalar for square and wide
matrices, while for tall
matrices their variation results from unevenly distributed row energy after orthogonalization. Under approximate orthogonalization, the orthogonality residuals introduce additional variation into the scaling, giving rise to a counterintuitive Orthogonalization–Adaptivity Paradox: more accurate orthogonalization weakens adaptivity. We further show that NorMuon's rigid row-wise scaling is geometrically misaligned with the one-sided orthogonal structure of tall
matrices by distorting column orthogonality. Motivated by these limitations, we propose two core design principles that a desirable adaptive mechanism for
Muon should satisfy. First, adaptive scaling should be decoupled from orthogonalization, with the scaling factors computed directly from raw gradients. Second, adaptive scaling should be aligned with the shape-dependent orthogonal structure of the polar factor, using row-wise scaling for wide
matrices and column-wise scaling for tall
matrices. We prove that this geometry-aligned scaling preserves the orthogonal structure of the update. By incorporating several other techniques, we obtain Decoupled Geometry-Aligned
Muon (DGA-
Muon). We establish convergence guarantees for DGA-
Muon and empirically validate both our theoretical characterization of NorMuon's scaling degeneration and the superiority of DGA-
Muon.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning
Qizhen Lan, Mengchen Fan, Hang Zhang et al. (+5 more)
Brain MRI interpretation is a longitudinal clinical
reasoning problem: radiologists compare serial studies, integrate information across MRI sequences, localize findings within volumetric anatomy, and translate this evidence into report-grounded assessments. Existing medical VQA and 3D imaging
benchmarks capture important parts of this workflow, but often evaluate
brain MRI through isolated images, static volumes, or ungrounded report-style answers, thereby obscuring failures in the evidence chain that support clinical validity. We introduce BrainTRACE, a report-grounded
benchmark for evaluating whether
vision-
language models can trace the evidence structure required for longitudinal
brain MRI interpretation. BrainTRACE contains 7,273 scored VQA instances derived from 1,778 longitudinal patients, 7,299 MRI studies, and approximately 29k co-registered 3D MRI sequence volumes. The
benchmark is organized by five levels of clinical
reasoning, from acquisition recognition to case-level synthesis, and by evidence demands covering longitudinal comparison, report-grounded references, multi-sequence integration, and volumetric spatial evidence. BrainTRACE supports rendered inputs compatible with standard VLM interfaces, a 3D-evidence condition, and a decomposed case-
reasoning track that audits six steps in a longitudinal evidence chain. Evaluation of 20 VLM configurations shows that current systems can identify isolated visual cues but rarely compose them into grounded longitudinal interpretations. We release the
benchmark specification, evaluation lists, scoring implementation, scoring rubrics, and audit-record format to support reproducible progress in
brain MRI VLM evaluation.
Read the full abstract ▾
All authors Qizhen Lan, Mengchen Fan, Hang Zhang, Jingwei Duan, Moule Lin, Jialin Chen, Baocheng Geng, Xiaoqian Jiang
Artificial Intelligence
HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention
Han Luo, Bingbing Wen, Guang Yang et al. (+3 more)
Large
language model (LLM)
agents are increasingly capable of acting in complex tool-use environments, yet they often fail to recognize when tasks are infeasible and no valid solution exists. Recent work has formalized this reliability gap as the problem of agentic abstention, and existing approaches typically optimize a model or
agent harness against a fixed set of tasks, leading to limited generalization to unseen failure modes. We introduce HERA, a framework for harness-environment co-
evolution for agentic abstention. HERA consists of (i) a pipeline to automatically construct verifiable pairs of feasible and infeasible tasks by applying controlled environment mutations that transform solvable tasks into cases requiring abstention, and (ii) a co-
evolution procedure in which performance failures on previous tasks are used to drive harness adaptation and generate new execution environments and tasks geared towards previous weaknesses. On held-out evaluation tasks, an evolved harness from HERA improves abstention accuracy from 61.7% to 83.3% while improving feasible-task completion from 68.3% to 76.7%, achieving the highest abstention and feasible-task completion among the compared methods. The resulting best harness transfers across 19 other LLMs, improving abstention accuracy by 15.3 percentage points on average without any model-specific optimization, and enabling smaller models to match the performance of more powerful models at an estimated 85% lower cost.
Read the full abstract ▾
All authors Han Luo, Bingbing Wen, Guang Yang, Zora Zhiruo Wang, Pan Lu, Lucy Lu Wang
Artificial Intelligence
Signature-Based Feature Learning for Human Activity Recognition: A Reproducible Machine Learning Study of Representation, Depth, and Model Choice
Kamal Jarrar, Jacky Cresson and Christian Paroissin
Human activity recognition (HAR) relies on transforming sensor signals into informative representations for classification. Although deep learning and handcrafted features are widely used, the role of representation itself is often not systematically isolated. Signature transforms provide a mathematically grounded way to encode temporal order and cross-channel interactions, but their value for HAR under a fully reproducible and leakage-aware framework remains unclear. To evaluate whether signature-based feature learning improves HAR performance compared with raw-signal baselines, and to assess the effects of
embedding strategy, truncation depth, model choice, and sensor configuration. Experiments were conducted on the UCI HAR
dataset using a fully reproducible pipeline with the original train–test split preserved and subject-disjoint validation to prevent leakage. Three representations were compared: raw flattened signals, time-augmented paths, and lead–lag transformed paths. Signature features were computed at multiple truncation depths and evaluated using multilayer perceptron (MLP) and Random Forest (RF) classifiers under identical preprocessing and validation procedures. A prior K-means-based feature reduction study was also reproduced for comparison. Signature-based representations improved performance when paired with RF models, the best configuration was time-augmented six-channel signatures at depth 6 using
entropy-based RF achieving 0.858 accuracy and 0.859 macro F1, outperforming the strongest raw baseline (0.816 accuracy). Lead–lag representations were competitive at moderate depths but did not surpass the best time-augmented models. MLP models did not exceed raw baselines. Signature-based feature learning can improve HAR, but its benefit depends on
alignment between representation design and classifier choice.
Read the full abstract ▾
Artificial Intelligence
Proof-Grounded Patient-Specific Clinical Explanations from Knowledge-Graph Reasoning
Surajit Das
Clinical decision-support outputs can lack an au- ditable link between patient observations, encoded knowledge, conclusions, and recommendations. We present the CKG Clinical Explanation Engine, a downstream layer for a frozen, training-free clinical knowledge-graph reasoner that converts patient inference states and disease knowledge into typed facts, explicit rule-application traces, provenance-linked conclusions, and policy-licensed recommendations. The design separates measurement availability, representation completeness, and disease-specific activation; consequently, observed zero-activation evience is not treated as missing and partial representation is distinct from unobserved evidence. Optional
language generation is restricted to symbolically licensed content. Across five usable workbooks (6,720 patients; 20,160 patient-disease traces; 1,021,440 feature-evidence rows), IG-range validity and knowledge provenance were 100%, numerical cross-sheet fidelity was 100% (120,960/120,960), and exported logical/report trace completeness was 100% (20,160/20,160). Availability representation consistency was 99.7028% (1,018,404/1,021,440); all 3,036 disagreements were confined to three systematic feature-cohort patterns. The corpus contained 86,783 observed zero-activation and 139,949 observed partially represented instances. A separate seeded 25-patient end-to-end audit completed without execution failure and passed all pre-specified trace, licensing, provenance, and state-consistency checks. These results establish structural and implementation auditability, not clinical correctness or utility.
Read the full abstract ▾