Artificial Intelligence
SpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers
Chenghao Yue, Siming Xing, Shuran Liu et al. (+2 more)
Two-
photon calcium imaging is a standard tool for recording large neural populations in vivo, yet inferring spikes accurately across the growing diversity of calcium indicators remains an open problem. Existing supervised methods achieve reasonable in-domain accuracy but generalize poorly to unseen indicators, because different indicators induce distinct fluorescence kinetics and signal statistics while existing architectures remain relatively simple generic temporal regressors without dynamics-matched inductive bias. We propose SpikeSSL, a universal spike inference framework whose temporal backbone is a bank of bidirectional IIR state-space layers broadly motivated by calcium dynamics. A multi-modal conditioning encoder maps indicator identity, sampling rate, and trace-level signal statistics into a global conditioning vector that modulates the backbone via Adaptive Layer Normalization, while a heteroscedastic variance head provides calibrated per-frame uncertainty. On a
benchmark with five fixed evaluation splits built from 33 public ground-truth
datasets, SpikeSSL achieves state-of-the-art performance in both in-domain and zero-shot leave-one-indicator-out settings. We also develop a biophysical simulation pipeline capable of generating paired fluorescence-spike traces with systematically varied kinetic parameters, spike statistics, response nonlinearities, baseline drift, and noise. Using this pipeline, we synthesize approximately 11,000 simulated traces. Augmenting training with these data effectively closes the cross-indicator domain gap and improves zero-shot generalization. Code is publicly available at https://github.com/detimage123/SpikeSSL.
Read the full abstract ▾
All authors Chenghao Yue, Siming Xing, Shuran Liu, Angran Li, Yuanlong Zhang
Artificial Intelligence · Cross-listed from cs.LG
Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains
Miruna Cretu, Alex Abrudan, Antonia Panescu et al. (+11 more)
Unified atomistic modeling has the potential to accelerate discovery in chemistry, materials science, and biology by bridging data-rich chemical domains and data-scarce biological contexts. However, existing generative approaches to atomistic modeling remain highly specialized to scientific disciplines (chemistry vs. biology) or do not leverage both high-volume organic (molecule) and inorganic (material) data for general-purpose pretraining. To this end, we introduce Zatom-2, an atomistic generative model pretrained on approximately five million structures from the OMol25 and OMat24 electronic structure
datasets. Zatom-2 features a multiscale
Transformer architecture coupled with conditional flow matching that supports force conditioning and foundational pretraining tasks such as generation, structure prediction, and prediction of molecular and material energies and forces. Empirically, Zatom-2 achieves better molecular distribution fidelity than Zatom-1 and achieves strong performance on existing molecule and material generation
benchmarks. Zatom-2 demonstrates the ability to control sample generation across low- and high-force regimes, and enhances
protein generation in a low-data setting through joint generative-predictive pretraining and transfer learning, increasing
protein backbone designability in a length extrapolation setting from 67.8% without pretraining to 74.8% after finetuning on 2,000
protein domains.
Read the full abstract ▾
All authors Miruna Cretu, Alex Abrudan, Antonia Panescu, Tynan Perez, Rishabh Anand, N. Benjamin Erichson, Michael W. Mahoney, Samuel Blau, Joseph Jacobson, Rafael Gómez-Bombarelli, Rex Ying, Tuomas Knowles, Pietro Liò, Alex Morehead
Artificial Intelligence
Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual Learning
Chen Wu, Josh Passenger and Yin Song
We study how a coding
agent learns across a sequence of abstract
reasoning tasks. The
agent runs on a frozen foundation model inside a fixed harness and acts by writing and running Python and shell scripts. It retains no state across turns other than its written artifacts, so every thought it forms, carries, corrects or abandons leaves a trace, where a thought is any belief, rule or plan committed to a file. We let the
agent play ARC-AGI-3, a set of interactive
reasoning games that provide no instructions. Each game is a sequence of levels, and a strategy that clears one level can fail on the next, so every new level is in effect a new task. The
agent records what it learns as Python scripts and text notes, while the harness keeps a complete log of every action and observation. Our contribution is a measurement protocol that traces each thought through these files, from the task where it forms to the task where it is corrected or abandoned, applied to seven evaluation runs with three backbones from two model families. Scripts written for one task are almost never called again in a later task (33 of 630 references cross a task boundary), because most scripts embed the state of the current level. Instead, the
agent rewrites its knowledge into new scripts, keeping the general rules and dropping the level-specific details, and abandons 74% of the scripts it wrote before a boundary. The notes, which only the model reads, are never revised: the
agent appends without removing earlier claims, and the contradictions that accumulate are settled against the log. Because the log preserves everything, the
agent forgets selectively, not catastrophically. The most costly error is a hard-coded value carried into a task where it no longer holds. These findings come from the files the
agent wrote, without access to the model, and constitute a white-box analysis of how a coding
agent continually learns.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Closed-loop evaluation of LLM agents for embedded software development
Jorge García-Carrasco, Sergio García-Carrasco, Alejandro Maté et al. (+1 more)
Large
language models (LLMs) are increasingly deployed as coding
agents that edit files, run builds and tests, inspect execution results, and repair software iteratively. Embedded firmware is a demanding target because correctness depends on closed-loop behavior under sensing, timing, and safety constraints, not only on static source quality. Yet embedded-
agent evaluation remains limited and often emphasizes one-shot synthesis or offline correctness. We present a
benchmark for closed-loop evaluation of embedded coding
agents. Each task provides a plain-text engineering description, constrained workspace, and visible build-and-runtime surface. The
agent must translate requirements into implementation and self-verification steps, then iterate until the required device behavior is achieved. The suite contains five embedded-control tasks and four feedback scenarios: one-shot generation, realistic self-verification, CI-style red/green feedback, and oracle-style detailed feedback. The implementation targets simulated ESP32 firmware for reproducibility. We evaluate seven GPT-family and Qwen-family configurations across five tasks and four scenarios, with three repetitions per condition for 420 runs. gpt-5.4 has the highest pass rate among evaluated configurations but does not saturate the
benchmark; qwen3.5-27B is the strongest observed local model; and smaller local models degrade sharply in pass rate and search efficiency. These results suggest that capable local embedded coding
agents are emerging.
Read the full abstract ▾
All authors Jorge García-Carrasco, Sergio García-Carrasco, Alejandro Maté, Juan Trujillo
Artificial Intelligence
Why machines will still not rule the world
Jobst Landgrebe and Barry Smith
In our book Why machines will never rule the world [13, 14] we argue that arti- ficial general intelligence is mathematically impossible. This is because the human beings and the processes which exhibit intelligence are complex systems whose be- haviour cannot be captured by the kinds of models that we can generate with or without computers. Proponents of contemporary machine intelligence respond with two lines of argument: a theoretical one, grounded in the universal approximation
theorems for neural networks and the Church-Turing-Deutsch principle; and an em- pirical one, grounded in rapidly rising scores on standardized
benchmarks. In this communication we examine and reject both responses. First, we show serious issues in the physicalist counter-argument based on the Church-Turing-Deutsch principle. Second, we review recent evidence to the effect that prominent
benchmarks are compromised by training-data contamination, flawed test construction, and strate- gic optimization. Our central argument remains: That models required to perform cognitive behaviour in open-ended, thermodynamically complex and non-ergodic environments are not and will not become achievable.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Missing Modality-Aware Calibration for Trustworthy Brain Tumor Segmentation
Sol Lee, Hyunji Kim, Sungrae Hong et al. (+2 more)
Multimodal brain tumor segmentation typically leverages multiple MRI modalities, yet incomplete modality acquisition is common in clinical practice due to protocol heterogeneity and scan failures. Although recent methods maintain segmentation accuracy under missing modality conditions, they frequently overlook prediction reliability, leading to miscalibrated confidence estimates that hinder clinical adoption. Existing calibration techniques are largely modality-agnostic or assume that prediction difficulty decreases monotonically as additional modalities become available. However, in
brain tumor segmentation, prediction difficulty depends primarily on which modalities are absent rather than how many, leading to combination-specific and spatially heterogeneous calibration errors. To address this, we propose Missing Modality-Aware Local Temperature Scaling (MMA-LTS), a post-hoc voxel-wise confidence calibration method. It estimates a spatially adaptive temperature field conditioned on a modality-availability learnable
token and a voxel-wise difficulty score. Experiments on BraTS 2020 and FeTS 2024 show that MMA-LTS improves calibration while preserving the segmentation accuracy of state-of-the-art models across diverse missing-modality scenarios, thereby enhancing trustworthiness toward clinical deployment.
Read the full abstract ▾
All authors Sol Lee, Hyunji Kim, Sungrae Hong, Donghee Han, Mun Yi
Artificial Intelligence · Cross-listed from cs.RO
Rewiring Semantics, Dynamics, and Control: A Simple yet Effective Action-Centric Tri-Stream Transformer
Shuang Luo, Yilun Kong, Yunpeng Qing et al. (+5 more)
Vision-
Language-Action (VLA) models have emerged as a prominent framework for complex robotic manipulation, building on the strong semantic understanding of pretrained
Vision-
Language Models (VLMs). However, such VLM backbones offer insufficient physical dynamics priors, which limits the generalization capabilities of
robot policies. Recent efforts therefore integrate
video-generation World Models (WMs) into
robot policies through various strategies, using predictive dynamics to facilitate action generation. Despite these advances, harnessing semantic understanding and dynamics prediction as complementary guidance for action generation remains challenging. In this paper, we introduce $\mathrm{ACT}^3$, a simple yet effective Action-Centric Tri-Stream
Transformer that fuses semantic and dynamics information into control actions while preserving the distinct roles of context streams. Specifically, $\mathrm{ACT}^3$ enables the dedicated action expert to access VLM and WM representations through layerwise
attention, with each backbone attending only within its own stream. This straightforward interaction design maintains independent forward propagation in the context streams while allowing both backbones to be updated through control supervision. Experiments on both simulated and real-world robotic manipulation
benchmarks show that the proposed $\mathrm{ACT}^3$ yields results superior to its counterparts.
Read the full abstract ▾
All authors Shuang Luo, Yilun Kong, Yunpeng Qing, Yihang Jiao, Zhi Hou, Shunyu Liu, Xiaogang Wang, Dacheng Tao
Artificial Intelligence
Cognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes
Hao Li, Jinye Zhang, Bobo Li et al. (+5 more)
Affective computing has progressed from categorical emotion recognition to open-ended affective analysis with large
multimodal models. Yet affective science describes emotion as an unfolding process shaped by appraisal, regulation, and social interpretation, which remains underexplored computationally. We propose TRACE, a cognition-oriented framework that formalizes an affective episode through three interrelated stages: Condition, Affect, and Effect, integrating observable cues with cognitive factors such as internal stance and regulation of emotional display. Based on this formulation, TRACE-Bench evaluates
multimodal models in real-world social scenes through five tasks spanning grounded affect recognition, regulation decoding, cause
reasoning, effect
reasoning, and full-chain reconstruction, with 3,746 structured question-answer pairs over 646
videos. A matched human-model comparison reveals a substantial performance gap, while affect-specialized models also generally lag behind general-purpose MLLMs. Model outputs show recurring failures, including treating displayed behavior as genuine feeling and fabricating unsupported events during long-chain generation. We further propose TRACER, a cognition-grounded structured
reasoning method that couples each inference with explicit premises from factual observations, cognitive appraisals, and established upstream conclusions, forming a traceable graph of intermediate and target conclusions. TRACER outperforms all evaluated model baselines on each of the five tasks. Project page: https://cogaffc.github.io/TRACE
Read the full abstract ▾
All authors Hao Li, Jinye Zhang, Bobo Li, Mong-Li Lee, Wynne Hsu, Zheng Wang, Hao Fei, Min Zhang
Artificial Intelligence
Estimating Great Expectations Under Autoregressive Language Models with Potentials
Francesco I. Re, Shubhangi Ghosh, Tim Vieira et al. (+1 more)
Many applications of
language models hinge not on individual samples but on the expectation of a test functional under the model. Estimating such expectations reliably can be computationally expensive. In this paper, we show how to make estimation more efficient by exploiting the next-
token conditional probabilities which are available as a by-product of sampling. We do so through potentials: real-valued functions on prefixes that decompose the test functional additively. We construct an
estimator whose variance depends on the chosen potential, and derive conditions under which a potential reduces this variance. We then develop practical potentials for several estimands and applications, and demonstrate substantial variance reductions across several estimands at comparable computational cost.
Read the full abstract ▾
All authors Francesco I. Re, Shubhangi Ghosh, Tim Vieira, Ryan Cotterell
Artificial Intelligence
TypedBench: A Benchmark for Calibration, Framing Sensitivity, and Cost in System One Decision Models
Rahul Sharma, Andrew B. Duncan, Gaétan Marceau Caron et al. (+1 more)
System One models output calibrated probabilities over typed answers such as categorical choices, ordinal levels, or binary outcomes, via a non-generative interface. Software can act on these probabilities through thresholds, cost-weighted choices, and escalation rules. Consequently, if these probabilities are miscalibrated or wording-sensitive, the software ma take unintended actions leaving human operators with no textual rationale to inspect. Current evaluations largely report accuracy and calibration on public classification
datasets without a clear reference. We present TypedBench, a
benchmark for typed decision models like Jev built from seven policy-labelled generators and nine evaluation suites. We report accuracy as median and range across paraphrases, and calibration error relative to the finite-sample noise floor of a matched, perfectly calibrated predictor. We assess probability quality through selective prediction, ordinal proper scoring rules, and realised cost under asymmetric cost
matrices. We evaluate a hosted model, an open encoder, and a family of open decoders spanning 0.8B-9B parameters on identical items. The hosted model follows the stated policy but is wording-sensitive and systematically underconfident; under asymmetric costs, using its probabilities can be worse than taking its top answer. Decoders route exactly and are slow as options or questions are added. The decoder is least accurate on policy questions and degrades with more options. Overall, typed decision models must be evaluated jointly on policy adherence, wording robustness, probability quality, and induced decision outcomes.
Read the full abstract ▾
All authors Rahul Sharma, Andrew B. Duncan, Gaétan Marceau Caron, Sebastian J. Vollmer
Artificial Intelligence · Cross-listed from cs.SC
RISR: Residual-Informed Scientific Equation Discovery with Large Language Models
Haobo Li, Wenshuo Zhang, Wenxiao Zhao et al. (+6 more)
Symbolic regression combines structural search with numerical fitting, but aggregate fit scores do not describe how the remaining error varies across inputs. We introduce RISR, a residual-informed method that uses these error patterns to guide formula discovery and learn which corrections are worth fitting. A residual encoder compresses aligned inputs, targets, current predictions, and residuals into continuous
tokens that condition a
language model to propose formulas. For subsequent refinement, a dual-view relational encoder uses additive and regularized multiplicative residuals to predict the post-fit utility of candidate corrections. We evaluate RISR on scientific tasks from the LLM-SRBench. RISR achieves 63.57% and 38.50% ID accuracy at the 1% and 0.1% pointwise relative-error tolerances, respectively. The corresponding OOD accuracies are 56.07% and 38.24%. RISR outperforms the reported baselines using the same backbone. The results show that our residual-informed approach can improve numerical equation recovery.
Read the full abstract ▾
All authors Haobo Li, Wenshuo Zhang, Wenxiao Zhao, Eunseo Jung, Rui Sheng, Yushi Sun, Peiqin Zhuang, Hao Chen, Fenghua Ling
Artificial Intelligence
Environmental Feedback Modeling Matters: Rethinking Feedback Treatment in Agentic Hindsight Self-Distillation
Hangxi Guo, Fengyuan Liu, Yue Wang et al. (+4 more)
Reinforcement learning is commonly used to train
language agents in interactive environments, but cannot be directly applied when rewards are unavailable. Recent methods use environmental feedback as privileged context for hindsight self-
distillation, but our analysis suggests that simply conditioning the teacher on feedback is insufficient, motivating us to rethink how environmental feedback is used in agentic self-
distillation. Given that environmental feedback contains rich supervision for modeling how the environment responds to
agent actions, we introduce agentic SElf-
distilLation with environmental Feedback modeling (SELF), a framework that jointly optimizes environmental feedback modeling and hindsight self-
distillation. SELF learns to predict environmental responses while distilling guidance from a feedback-conditioned self-teacher into the policy. Our analysis reveals a mutually reinforcing mechanism: environmental feedback modeling strengthens hindsight supervision and policy learning, while self-
distillation enhances the model's ability to model environmental feedback. With Qwen3-8B, SELF outperforms SDPO and GRPO by 6.4 and 4.1 percentage points in $\tau$-bench success rate, and by 10.71 and 3.57 percentage points in AppWorld task goal completion, respectively. These results show that SELF uses environmental feedback more effectively within agentic self-
distillation, improving
agent capabilities.
Read the full abstract ▾
All authors Hangxi Guo, Fengyuan Liu, Yue Wang, Yuhua Qi, Haoyi Xiong, Fei Sun, Mengnan Du
Artificial Intelligence · Cross-listed from cs.CV
EvoKnow: Continual Knowledge Evolution for AI-Generated Image Detection
Zhiheng Peng, Wenwei Jin, Yangshi Ge et al. (+3 more)
AI-generated image detectors are commonly trained on fixed generator domains and become difficult to maintain as new generative models emerge. Continual adaptation is challenging because replaying historical generated images is costly, whereas updating shared parameters with limited current-domain data can overwrite prior forensic knowledge. We propose EvoKnow, a replay-free framework that formulates continual AI-generated image detection as forensic knowledge
evolution. EvoKnow preserves a shared forensic basis learned from base domains, incrementally adds isolated residual experts for complementary generator-relevant evidence, and retrieves expertise through an Analytical Incremental Router (AIR) updated in closed form from current-stage generated images and accumulated sufficient statistics. Experiments demonstrate effective cross-generator generalization, few-shot expansion, and long-horizon continual adaptation. With ten generated images per arriving generator, EvoKnow achieves 96.70% average accuracy on non-base GenImage generators and 94.48% accuracy on Chameleon without target-
benchmark adaptation. Under a strict replay-free continual learning protocol, EvoKnow achieves state-of-the-art continual learning performance, attaining 96.32% mean stage-wise accuracy and 4.32% average forgetting.
Read the full abstract ▾
All authors Zhiheng Peng, Wenwei Jin, Yangshi Ge, Siyu Xia, Jiawei Li, Xu Tang
Artificial Intelligence
Equal Path Cost, Unequal Output Effects: Understanding Perturbation Propagation in Diffusion Models
Wei Guo, Yaowen Zhang, Xingtong Ge et al. (+1 more)
Diffusion models have achieved remarkable success in generative modeling, with their sampling procedures routinely modified to control generation and improve efficiency. These modifications introduce perturbations along the sampling trajectory, raising a central question: how do such perturbations affect generated output? To address this question, we develop a theoretical framework to investigate perturbation propagation, combining dynamical analysis of the sampling process with an information-theoretic characterization of output responses. Within this framework, we quantify perturbation strength using the Kullback–Leibler (KL) divergence between perturbed and reference trajectory distributions, termed as path cost, which is shown to bound, but do not determine, changes in the output distribution. Building on this analysis, we derive a response identity that connects the propagation and accumulation of local perturbations with the information captured by a selected feature mean, explaining why changes in the output distribution can remain undetected by its first-order response. We test our theoretical analysis through controlled interventions at equal path cost in pretrained
diffusion models, revealing distinct patterns of output sensitivity across sampling stages and spatial frequencies. To assess whether our framework can diagnose perturbations arising from practical approximations, we apply it to cache-based acceleration and show that our propagation analysis reliably identifies sampling intervals where caching causes larger image errors.
Read the full abstract ▾
All authors Wei Guo, Yaowen Zhang, Xingtong Ge, Jun Zhang
Artificial Intelligence · Cross-listed from cs.CV
CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding
Andrea Ceron, Michael Schmidt, Alvaro Marcos-Ramiro et al. (+2 more)
Latent
LiDAR pipelines suffer from flying pixels: convolutional VAEs blur sharp radial depth discontinuities, yielding edge depths that back-project to points floating between surfaces. We identify this as a major, directly correctable decoder bottleneck and introduce CRISP: a pixel-space
diffusion decoder with a backbone-agnostic latent adapter, DiT-based denoiser, and support mask predictor. CRISP replaces
video-VAE and
LiDAR-native decoders alike while keeping the encoder and latent generator fixed. Across KITTI-360, SemanticKITTI, and nuScenes, replacing only the decoder reduces FSVD/FPVD by 50.5% on average across frozen backbones; for generic
video VAEs, the reductions reach 71%/74%. On the
LiDAR-native LiDM backbone, FRID drops by 71%, with the largest gains at depth discontinuities. In a pretrained LiDM world model, the same zero-shot replacement improves FSVD by 15.5%, narrowing the sim-to-real gap.
Read the full abstract ▾
All authors Andrea Ceron, Michael Schmidt, Alvaro Marcos-Ramiro, Sebastian Schmidt, Benjamin Busam
Artificial Intelligence · Cross-listed from cs.CV
Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder
Zidan Wang, Yaqian Li, Xiaokai Zhang et al. (+3 more)
CLIP serves as a foundational
vision-
language model and the de facto
vision encoder for downstream VLMs such as LLaVA. Post-training offers a lightweight route to refine CLIP, but recent work argues that the standard contrastive loss is unsuitable for post-training due to catastrophic forgetting under small batches, motivating designs that abandon the contrastive objective in favor of
distillation. We revisit this premise and find that, for the InfoNCE objective, the reported forgetting is driven primarily not by insufficient negatives but by an inappropriate magnitude of the contrastive temperature $\tau$: with $\tau$ set sufficiently small, contrastive post-training improves rather than degrades the pretrained CLIP, which we explain through the temperature dependence of the InfoNCE gradient. Building on this finding, we propose ComCLIP, a lightweight single-epoch post-training recipe that freezes CLIP's text encoder—so the refined
vision encoder is a drop-in replacement with unchanged architecture and inference cost—and trains the
vision encoder with a properly-tempered contrastive loss, an MSE anchoring loss against the original CLIP, and a relational
distillation loss from DINOv2. Over multiple seeds, ComCLIP matches the self-
distillation baseline CLIP-Refine on zero-shot classification while significantly improving the transferability of visual features, measured by linear probing ($48.99$ vs.\ $42.28$ on ViT-B/16), and on ViT-L/14 it also improves MMVP over CLIP-Refine ($24.20$ vs.\ $19.01$); CLIP-Refine remains stronger on image-text
retrieval. Used as a drop-in
vision encoder for LLaVA-1.5-7B without re-aligning the projector or LLM, ComCLIP yields no net change across $8$ VLM
benchmarks, i.e., the refinement does not break downstream compatibility. Code and models are available at https://github.com/showstarpro/ComCLIP.git.
Read the full abstract ▾
All authors Zidan Wang, Yaqian Li, Xiaokai Zhang, Kaiwen Long, Kun He, Hanpeng Liu
Artificial Intelligence
RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees
Meghanadh Pulivarthi, Swaraj Kumar Biswal, Kushagra Bhushan et al. (+3 more)
Retrieval-augmented generation (RAG) grounds
language models in external corpora. Agentic RAG enables iterative search, yet exposes the model to isolated chunks without document structure, making it difficult to distinguish relevant evidence from chunks that merely resemble the query. Structure-aware methods such as PageIndex navigate document structure but cannot scale to the structures of large corpora, which do not fit in the LLM context. Hence, they first commit to a single document using a document retriever and cannot recover from a wrong choice. We propose RIT-RAG (
Retrieval-Induced Tree RAG), which combines content
retrieval with structural navigation. Offline, RIT-RAG builds a tree for each document from its table of contents or sitemap. At query time, it retrieves a broad set of chunks and uses their positions to induce manageable sub-trees, potentially across multiple documents. An LLM
agent navigates these sub-trees, selectively reads promising nodes, and reformulates queries when needed. Thus,
retrieval proposes where to look, while the
agent decides what to read. Across financial, scientific, and customer-support
benchmarks, RIT-RAG achieves the highest answer accuracy among vanilla, graph-based, and agentic baselines. On EntQABench, our new
benchmark of 2.84 million technical-documentation webpages, it improves accuracy by 6.8 to 11.4 points over the strongest baseline across three LLMs.
Read the full abstract ▾
All authors Meghanadh Pulivarthi, Swaraj Kumar Biswal, Kushagra Bhushan, Yatin Nandwani, Sachindra Joshi, Dinesh Raghu
Artificial Intelligence
UniData: Universal Multimodal Instruction Generation Pipeline
Jiaqi Tang, Yi-Feng Wu, Yuting Zhang et al. (+12 more)
Multimodal Large
Language Models (MLLMs) are increasingly being applied in a wider range of real-world scenarios. However, due to the substantial labor cost, creating high-quality
multimodal instruction
datasets for MLLMs remains a significant challenge. Although some methods propose to generate instruction data, they often face limitations in modality support and struggle with generating multi-round instructions. To address these problems, we introduce UniData, a universal instruction generation pipeline, to transform simple user requirements into multi-round,
multimodal instructions. Specifically, UniData first expands user requirements into multiple diverse events. Using these events, UniData then integrates an any-to-any large model for
multimodal instruction generation. Finally, UniData enhances data quality by correcting irrelevant and redundant inference flow, leveraging correlations between instruction rounds. To train this pipeline, we also build UniDataset, a
dataset comprising 20,000 entries across nine modalities for improved
multimodal generation. Our experiments demonstrate that UniData achieves SOTA performance in data quality and can also enhance the understanding and generation capabilities of other
multimodal models.
Read the full abstract ▾
All authors Jiaqi Tang, Yi-Feng Wu, Yuting Zhang, Hao Lu, Bowen Fu, Qing-Guo Chen, Xiaogang Xu, Yuwei Hu, Shiyin Lu, Wei Wei, Lei Zhang, Zhao Xu, Weihua Luo, Qifeng Chen, Ying-Cong Chen
Artificial Intelligence
RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation
Sreetama Sarkar, Saptarshi Mitra, Sitao Huang et al. (+2 more)
Cross-model KV-cache reuse remains a key challenge in modern LLM serving. Coding
agents and multi-model systems increasingly route a shared context across models: a user may switch models mid-session, or a cascade may escalate a difficult query. Because KV caches contain model-specific representations, each switch typically forces the receiving model to prefill the entire context from scratch. Recent work shows that closed-form linear maps can translate KV caches between models in the same family, but transfer accuracy degrades as the model-size gap widens. In this paper, we establish that these transfer failures are concentrated in a small subset of information-dense
tokens. To bridge this gap, we introduce RaReCache, a framework that enables a large target model to decode accurately from a cache prefilled by a much smaller source via selective recomputation. RaReCache identifies these critical positions using a novel rank disagreement metric, scoring each
token by the energy of its mapped KV in output directions weakly supported by the calibration data. Across two model families and five
benchmarks, on a 23x parameter gap (Qwen3-0.6B to 14B) recomputing just 30% of positions retains 95-99% of the target accuracy, whereas on a 8.8x gap (Llama3-8B to 70B), recomputing 40% retains 96.5% of the target accuracy. RaReCache largely removes sensitivity to source-model size, and achieves up to a 3.04x prefill speedup. For online serving, it handles 1.8x the request throughput of target prefill on a single GPU, and at the target's saturation load, reduces median and 99th-percentile time-to-first-
token (TTFT) by 5.0x and 6.4x respectively, with a 30% recompute budget. RaReCache establishes an efficient serving paradigm where small models prefill on behalf of massive targets, enabling large models to recompute only critical
tokens, drastically reducing prefill latency.
Read the full abstract ▾
All authors Sreetama Sarkar, Saptarshi Mitra, Sitao Huang, Souvik Kundu, Peter A. Beerel
Artificial Intelligence
Defensive Writing in GPT Models
Junchi Liao, Xiao Huang, Yucheng Liu et al. (+2 more)
Researchers increasingly use ChatGPT to revise their papers, and when asked to make a paper hold up under review, recent GPT versions often narrow or even retract the authors' claims. We call such changes defensive writing when the given material does not support them, and we test two explanations: the model corrects the authors' overclaiming, or it writes for an anticipated reviewer. We ask GPT versions and models from other developers to rewrite paragraphs from papers written before ChatGPT, or to write from an evidence sheet that lists a paper's method and results. From GPT-5.5 on, GPT versions add clearly more ungrounded qualifications than the authors' originals contain, and GPT-6-astra adds the most and often retracts the authors' claims. Each explanation fits one part. Checked against the full papers, GPT-6-astra's retractions mostly correct overstated claims or explanations, but most added qualifications are redundant. The qualifications follow the request: they are absent under polishing, appear with any request to check the claims, and peak when the
prompt names a reviewer's concerns. AI reviewers score such rewrites higher and score them lower once only the qualifications are removed, while human readers in a small study find them harder to read. Combining AI writing with AI review may reward qualifications that readers pay for.
Read the full abstract ▾
All authors Junchi Liao, Xiao Huang, Yucheng Liu, Jiawen Deng, Fuji Ren
Artificial Intelligence
RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty
Gukhyeon Lee and SangKeun Lee
Language models (LMs) are commonly trained with Reinforcement Learning with Verifiable Rewards (RLVR) to enhance their
reasoning capabilities. However, since RLVR does not explicitly account for calibration during training, it can lead to severe calibration degradation, including overconfidence. Recent calibration-aware training methods for LMs, which incorporate objectives for uncertainty estimation into training, improve calibration but still exhibit overconfidence under distribution shift, while sacrificing
reasoning performance. To this end, we propose RL-ARC, a calibration-aware training framework that jointly leverages
reasoning confidence and answer confidence. Specifically, RL-ARC leverages
reasoning confidence as an auxiliary signal for calibrating answer confidence, applying it as
reasoning-guided regularization for correct cases and as an overconfidence penalty for incorrect cases. Comprehensive results across ID and OOD settings show that, beyond improving calibration, RL-ARC enables
reasoning models to adaptively estimate confidence based on the given question without substantially sacrificing
reasoning performance, thereby highlighting the importance of
reasoning confidence for training reliable
reasoning models.
Read the full abstract ▾
Artificial Intelligence
SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning
Wei Yang, Shawn Li, Yuehan Qin et al. (+8 more)
Self-evolving LLM
agents promise to improve autonomously through continual interaction and learning, reducing their dependence on manually curated supervision. Realizing this promise requires not only updating the
agent, but also evolving its training experience as its capabilities change. However, most existing pipelines rely on static
datasets or separately updated synthesis models, causing previously useful tasks to become trivial while overly difficult tasks remain uninformative. This growing mismatch between
agent capability and training experience limits sustained self-improvement. To address this problem, we propose SynCo, an agentic data synthesis co-training framework for self-evolving LLMs based on multi-
agent reinforcement learning. SynCo jointly optimizes two independently parameterized
agents: a Synthesizer that constructs training tasks from the Reasoner's evolving capability state, and a Reasoner that learns from the resulting experience. Each synthesized task induces multiple Reasoner rollouts whose outcomes provide complementary rewards to both
agents. Correctness feedback improves the Reasoner, while task quality, answer reliability, and outcome-grounded teachability guide the Synthesizer. Their updates are fed back into subsequent synthesis rounds, allowing the task-solving policy and its training distribution to evolve together. Extensive experiments across eight mathematical
reasoning benchmarks demonstrate that SynCo substantially outperforms a broad range of existing synthetic-data methods and controlled baselines, achieving the strongest overall performance while deriving most of its gains from previously unsolved problems.
Read the full abstract ▾
All authors Wei Yang, Shawn Li, Yuehan Qin, Yawei Wang, Mingxi Wang, Shixuan Li, Tiankai Yang, Jiate Li, Jesse Thomason, Xuezhe Ma, Yue Zhao
Artificial Intelligence
EvoSim: Learning to Model, Modeling to Learn
Yun-Wei Song, Jinkai Tao, Jun-Dong Zhang et al. (+3 more)
Physics-based models connect scientific explanation with quantitative prediction. Constructing them requires selecting physical processes, defining states and governing equations, specifying couplings, and identifying parameters from experiments. Existing AI systems remain limited in making these model structure decisions autonomously. We introduce EvoSim, a self-evolving AI scientist for physical modeling. It uses experimental discrepancies to drive mechanism and equation revisions and held-out experimental data to test physical plausibility. Exploration traces make updates to knowledge, skills, and multi-
agent orchestration. This co-
evolution improves physics-based models and EvoSim's ability to select mechanisms, diagnose failures, and coordinate research. We evaluate EvoSim on two industrial battery modeling tasks. It predicts lithium-metal-plating onset from 25 to 45 degrees Celsius and 2 C to 6 C with a mean absolute error of 1.79% in state of charge. Dynamic voltage prediction under vehicle driving conditions achieves a root mean square error of 7.62 mV, surpassing the reported accuracy of models developed by human experts. Self-
evolution reduces model and physics errors by approximately 36% relative to baseline, demonstrating improved scientific modeling capability. EvoSim turns experimental observations into validated models and cumulative research expertise.
Read the full abstract ▾
All authors Yun-Wei Song, Jinkai Tao, Jun-Dong Zhang, Rui Zhang, Yi-Min Wu, Qiang Zhang
Artificial Intelligence
ReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems
Weilin Jin, Mingyu Wang, Taiyu Zhu et al. (+7 more)
In LLM-based
agent systems, failures can originate from early steps whose effects propagate through subsequent interactions, making their origins difficult to identify. To trace such failures back to their origin, failure attribution has been formulated as the task of identifying the earliest step responsible for the failure. Recent methods leverage LLM internal signals for failure attribution, typically using hidden states as step representations. We therefore conduct an empirical study to evaluate how effectively these representations distinguish root-cause steps from other steps and find limited separation. Motivated by this observation, we propose ReCast, a step representation learning method that transforms hidden states from a frozen LLM into attribution-oriented step representations. ReCast first selects attribution-relevant layers, then constructs complementary pattern and deviation features, and finally learns contextualized step representations through an encoder trained with contrastive and ranking objectives. We also introduce ReCast-2K, a training
dataset for failure attribution. ReCast achieves the best Hit@1 across four
benchmarks, surpassing the strongest baseline by 5.65 and 9.19 pp on Who&When
Algorithm and Handcrafted, respectively. Code is available at https://anonymous.4open.science/r/ReCast-5FB6 .
Read the full abstract ▾
All authors Weilin Jin, Mingyu Wang, Taiyu Zhu, Ziqi Zhou, Wenbo Li, Haoyang Huang, Nan Duan, Yifan Wu, Ying Li, Zhonghai Wu
Artificial Intelligence
TokenBank: Financial Infrastructure for AI Services
Cary Chang and Jialin Zhou
AI services incur inference costs during execution, while revenue may arrive later. Changing API prices, limited upfront capital, and service failures can limit operators' ability to sustain or expand their services. Beyond reducing per-request costs, operators need to plan future spending, fund execution before revenue arrives, and obtain compensation for specified losses. This requires clear agreements across services with different pricing and execution conditions. These agreements must distinguish rights to consume services from rights to receive payments, define obligations under uncertain costs and income, and specify which failures qualify for compensation and how much can be paid. We present TokenBank, a financial infrastructure that represents these commitments through structured contracts. It supports service-consumption rights, agreements that settle API-price differences in cash (forwards), financing through limited rights to future service revenue, and protection claims for specified service failures. Contracts specify participants, covered services, validity, ownership, fulfillment conditions, and settlement rules. Evaluation combines replay of 899,441 API requests, real model-driven
agent execution, and contract API tests. In a zero-discount rising-price resampling scenario, forwards reduce mean expenditure by USD 304.88 but increase its standard deviation from USD 1,152.45 to USD 1,190.82. A controlled replication with five portfolios per capital condition finds mean contribution differences between financing and self-funding of +1.0635, -0.1406, and -0.2962 experimental USD under low, baseline, and ample capital, respectively. The evaluation distinguishes contract correctness from economic effectiveness under declared economic and failure assumptions; supplier invoices and commercial revenue are unavailable.
Read the full abstract ▾
Artificial Intelligence
Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild
Yuxuan Cao, Junlong Li, Hao Li et al. (+1 more)
Advances in foundation models are driving efforts to introduce
agents to assist people in the physical world. Such
agents require agentic spatial intelligence: exploring unfamiliar environments, updating spatial understanding through interaction, and adapting actions based on feedback to sustain progress toward a sequence of goals. Existing
benchmarks cover only a limited range of spatial layouts, scales, and traversal requirements. We introduce Mine Odyssey, a
benchmark for evaluating agentic spatial intelligence using Minecraft reconstructions of real-world locations. It comprises 180 tasks covering 30 such locations across 20 countries and regions on five continents, including 20 outdoor and 10 indoor settings. These settings span diverse spatial scales, layouts, terrains, and connectivity patterns, from Midtown Manhattan and rural Entrup to Santa Lucía Hill and Buckingham Palace. We select meaningful waypoints, such as landmarks, buildings, and rooms, and manually verify their accessibility. Each task provides a natural-
language instruction specifying which waypoints to visit and in what order. Completing these tasks requires
agents to find accessible routes and entrances, open doors, and move between levels using stairs and ladders, while monitoring their progress and recovering from navigation errors. Across eight evaluated state-of-the-art models, GPT-6 Astra achieves the highest success rate of 85.6%. However, the second-best model, Claude Opus 5.5, completes 73.9% of tasks, while the strongest evaluated open-weight model, DeepSeek-V4.1-Flash, reaches 23.9%, highlighting substantial room for improvement in the agentic spatial intelligence of current models. Comprehensive analyses and ablation studies on Mine Odyssey reveal current models' limitations and provide insights for advancing agentic spatial intelligence.
Read the full abstract ▾
All authors Yuxuan Cao, Junlong Li, Hao Li, Junxian He
Artificial Intelligence
Finsler Flow Matching: Dynamics-Aware Geodesic Interpolation for Single-Snapshot Trajectory Inference
Niklas Canova and Jonas Simon Fleck
Single-
cell snapshot data can resolve a continuum of cellular states but do not uniquely determine the dynamics governing transitions between them. However, additional dynamical information can often be encoded in a
cell-
cell Markov transition kernel. Existing generative approaches for single
cell trajectory inference either infer transport only from population marginals, impose a symmetric geometry on the state space, or incorporate directionality through a single velocity vector at each observed state. We introduce Finsler Flow Matching (FFM), a framework for learning continuous
stochastic dynamics from discrete Markov transition graphs. We use the first and second local moments to construct a Finsler structure motivated by the Freidlin–Wentzell action, where the second moment determines anisotropic accessibility and the first moment introduces a preferred direction of motion. We learn neural approximations of the resulting directed geodesics, use their Finsler cost to construct source-target couplings, and define geometry-aware
stochastic conditional paths that can be distilled into a continuous generative process through simulation-free score and flow matching. Across synthetic and single-
cell trajectory inference
benchmarks, FFM improves recovery of withheld intermediate populations, particularly when the transition dynamics are strongly directional or anisotropic. Our results provide a principled route from discrete transition probabilities to continuous generative dynamics while retaining both directional and diffusive structure.
Read the full abstract ▾
Artificial Intelligence
DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition
Yuxuan Lou, Kai Yang, Geng Zhang et al. (+2 more)
Mixture-of-Experts (MoE) architectures have become essential for scaling large
language models, with recent work demonstrating the benefits of fine-grained expert designs. Training such models from scratch is expensive, and sparse upcycling from pre-trained dense models is an attractive alternative. However, we identify a structural pathology of fine-grained upcycling: when fine-grained experts are derived from a single source model, naive routing collapses and downstream accuracy drops to near-random (e.g., on Qwen3-1.7B, Drop-Upcycling-fine-grained reaches only 23.2% average accuracy across 15
benchmarks, essentially matching from-scratch training at 22.2%, while the same method's coarse-grained variant reaches 50.2%). We propose DivMoE, the first framework achieving fine-grained MoE Upcycling with structurally-balanced routing. DivMoE introduces domain-specialized fine-grained expert initialization, deriving experts from dense models that have undergone domain-adaptive continual pre-training, and diversity-constrained routing, a hard structural constraint guaranteeing that each
token activates experts from distinct domain groups. Across two base models and 15
benchmarks, DivMoE consistently outperforms six upcycling baselines (55.6% vs. 51.6% for the strongest baseline on Qwen3-1.7B) and strictly improves over the dense base model on every
benchmark after Stage 2 continual pre-training – closing the regression gap that has plagued prior fine-grained upcycling. After supervised fine-tuning on a public
reasoning mixture, our 12B-parameter DivMoE model matches Moonlight-MoE (16B) at 64.5% average accuracy while outperforming a controlled NVIDIA-Upcycling baseline by 6.1 percentage points.
Read the full abstract ▾
All authors Yuxuan Lou, Kai Yang, Geng Zhang, Yong Liu, Yang You
Artificial Intelligence · Cross-listed from cs.CL
MetaEncoder: Exploring the Limit of Bi-Encoders for Multimodal System One Decision Making with Natural Language Interface
Jianpeng Cheng, Guangyu Sun, Aashu Singh et al. (+11 more)
System One models output constrained decisions and probability distributions rather than free-form text generation. While prevailing paradigms rely on structured schema objects to encode state, intent, and candidate choices, we revisit a fully natural
language-based System One interface. In this framework, both the user request and each candidate option are expressed in natural
language, supported by
multimodal (image and
video) auxiliary inputs. We introduce MetaEncoder, which fine-tunes a pre-trained Muse-Glimmer 30B decoder into an instruction-following decision-making encoder. To scale effectively across both small closed-set (< 256) and massive open-set (millions) candidate spaces, MetaEncoder employs a bi-encoder architecture trained via unidirectional contrastive learning for request-candidate
alignment. We conduct extensive evaluations across 11
benchmark suites and 190 tasks spanning
multimodal decision-making, understanding (closed-set) and
retrieval (open-set), highlighting where MetaEncoder beats SOTA
multimodal encoders, as well as its current limits on
reasoning-intensive tasks.
Read the full abstract ▾
All authors Jianpeng Cheng, Guangyu Sun, Aashu Singh, Benyu Zhang, Haixing Dai, Hossein Mansour, Jiangfan Zhang, Shlok Kumar Mishra, Wei Sun, Xuanming Cui, Yanli Liu, Qi Guo, Max Xiangjun Fan, Jun Xiao
Artificial Intelligence
MedBenchAgent: Towards Systematic Automation of Medical VLM Benchmark Construction
Yulin Fu, Junren Wang, Guangjing Yang et al. (+5 more)
Large-scale construction of medical
vision-
language model (VLM)
benchmarks is increasingly feasible with richly annotated imaging
datasets and large
language models (LLMs), yet existing automation largely focuses on generating evaluation items within predefined
benchmark specifications. We study the broader problem of automatically deriving the specification itself: what to evaluate, which annotations support each task, and how to translate this evidence into reliable evaluation items. We formulate
benchmark construction as constrained compilation, in which the
benchmark specification is progressively derived from evaluation requirements, heterogeneous annotations, and medical knowledge. Based on this formulation, we introduce MedBenchAgent, a multi-
agent framework with a
Benchmark Intermediate Representation (BIR) that encodes task definitions, evidence mappings, evaluation protocols, and item specifications across construction stages. MedBenchAgent separates planning, which derives and verifies the specification, from instantiation, which constructs and audits items under the locked specification. MedBenchAgent achieves a Task-Space F1 of 90.9%, outperforming direct task induction (79.2-80.0%) and prior-guided induction (85.1%); 994 of 1,000 sampled items from correctly identified tasks pass human audit. We further demonstrate portability to a specialized medical domain and evaluate twelve VLMs, revealing task- and setting-specific variation obscured by aggregate scores. These results establish constrained compilation as a scalable and auditable framework for medical VLM
benchmark construction beyond question generation.
Read the full abstract ▾
All authors Yulin Fu, Junren Wang, Guangjing Yang, Zhangyuan Yu, Wanran Sun, Jiabao Zhou, Jin Yin, Qicheng Lao