Symbolic Computation
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
Data Structures and Algorithms
Tight bounds and output sensitive algorithms for maximal clique enumeration in link streams
George Manoussakis
A link stream is a set of interactions between pairs of vertices, each one lasting during some time interval, and a clique of a link stream is a set of vertices together with a time interval during which all of them interact. A clique is maximal if neither its vertex set nor its interval can be enlarged. All known
algorithms listing the maximal cliques of a link stream may spend time exponential in the size of a clique for each clique they output. Here, we approach the question under the light of two parameters of the instantaneous graphs of the stream, their maximum degree $\Delta$ and their degeneracy $k$. We prove that a link stream with $m$ links has $O(m\Delta^2 3^{\Delta/3})$ maximal cliques, and that a link stream with $n$ vertices and $|\mathcal{T}|$ distinct end times has $O(n|\mathcal{T}|k^2 3^{k/3})$ maximal cliques. Both bounds are tight up to a factor
polynomial in $\Delta$ and $k$ respectively, and the second one improves the factor $2^k$ of previous bounds to $3^{k/3}$. Then we present two
algorithms. The first one has setup time $O(m\log m)$ and
polynomial time delay $\mathrm{poly}(\Delta)\log m$. The second one has setup time $O(m\log m+mk^2\log^3 n)$ and
polynomial time delay $\mathrm{poly}(k)\log m$. To the best of our knowledge, these are the first
algorithms with
polynomial time delay for this problem. We also give an online version of the second
algorithm, and we show that our results apply to the $\Delta$-cliques and $(\Delta,\gamma)$-cliques of temporal graphs.
Read the full abstract ▾
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
Robotics
PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous Driving
Jinchang Xu, Hongda Yu, Fengwei Dong et al. (+9 more)
World models in end-to-end autonomous driving predict future scene
evolution to provide foresight for trajectory planning. Existing methods mainly study how to predict the future and how to use it, but less often ask which future representation is actually most useful for planning. To this end, we propose PlanWAM, a Planning-Shaped World Action Model. The key idea is to let the planning task shape the future-state representation, so that it retains the information most useful for planning. A latent world model then predicts this planning-shaped future latent representation from historical observations and uses it for planning, enabling foresighted planning. Specifically, we first use a Temporal Register Pyramid to compress multi-frame historical information in a recency-aware manner, learning a compact history representation oriented toward future
reasoning and planning. We then introduce a privileged future posterior branch that observes ground-truth future frames, and shape its future latent representation with trajectory-planning objectives to obtain a planning-shaped future latent representation. Hindsight-to-Foresight
Distillation trains a prior branch that depends only on history to predict this future latent representation. The predicted future latent representation serves as planning context and guides trajectory generation and selection. PlanWAM achieves 93.8 PDMS / 90.9 EPDMS on NAVSIM-v1/v2 navtest and reaches 38.7 HD-Score on closed-loop HUGSIM in a zero-shot setting, demonstrating leading planning performance across both open-loop and closed-loop evaluations. Extensive experiments further demonstrate that planning-shaped future representations provide an effective and deployable form of foresight for world-action models.
Read the full abstract ▾
All authors Jinchang Xu, Hongda Yu, Fengwei Dong, Wenhui Huang, Xi Wei, Yongzhi Liu, Sunan Zhang, Jirao Wang, Chen Lv, Bingbing Li, Guodong Yin, Weichao Zhuang
Computer Vision
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
Computer Vision
FastJEV: Understanding Redundancy for Compact JEV Inference
Jie Ma, Jie Gao, Yihang Liu et al. (+5 more)
JEV models make
multimodal decisions by directly scoring candidates. Although the common context is encoded once, candidate evaluation can still repeat matching
token histories, duplicate inference states, and execute the full backbone. In this paper, we study these sources of redundancy and present FastJEV for compact candidate evaluation. We jointly organize history reuse and state storage, since sharing computation requires preserving states for later branches. We first introduce shared context anchoring to reuse recurrent initial states and omit unused final recurrent caches. We extend this reuse through candidate prefix sharing, retaining the intermediate states needed by subsequent branches. To further reduce the depth of these paths, we apply decision guided
pruning based on relative score changes measured on a small unlabeled set. Our method retains full context encoding and all candidates without additional training. We evaluate FastJEV across three OmniJev model sizes on five public
benchmarks and reconstructed LIBERO-10 offline questions. At the selected
pruning budgets, the complete method reduces candidate depth by 43.75% to 45.83%, while retaining 93.66% to 97.52% of the original task scores on average across the six evaluation sets. Through controlled experiments, we show how candidate overlap and branching structure affect the execution cost of history reuse. In our implementation, candidate prefix sharing can reduce repeated computation while increasing latency. These findings motivate designing sharing granularity and execution schedules together for efficient JEV inference.
Read the full abstract ▾
All authors Jie Ma, Jie Gao, Yihang Liu, Zhike Qiu, Junle Li, Chongyi Zhuang, Jiayi Ji, Xiaoshuai Sun
Information Theory · Cross-listed from quant-ph
Minimal Scenarios Witnessing Genuine Multipartite Nonlocality Possibilistically
Soumyadip Patra and Peter Bierhorst
We study a strong form of genuine multipartite nonlocality (GMNL), where an $n$-partite scenario admits a
quantum strategy generating outcomes belonging to a restricted set with certainty, whereas every strategy built from nonclassical resources shared among at most $k<n$ parties fails this criterion with positive probability. This generalizes what is referred to as strong contextuality/nonlocality, or pseudotelepathy, beyond ruling out local models. For the simplest five-party Bell scenario of two binary-outcome measurement settings per party, we use the inflation technique to demonstrate that a game with a perfect
quantum strategy witnesses a robust separation from models built from bipartite resources under local operations and shared randomness (LOSR), establishing the behavior is LOSR-GMNL. We provide broader context for this result by investigating its simulability with resources shared among three or four parties under different resource models and alternative definitions of GMNL. A central open question is whether $n$-party
quantum resources can achieve such a separation from models built from $(n-1)$-party resources, for $n\ge 3$. We make progress here by constructing a family of robustly LOSR-GMNL games with $\epsilon$-optimal
quantum strategies experimentally indistinguishable in the limit from true probability-one-winning strategies for any desired level of precision.
Read the full abstract ▾
Computer Vision
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. Code and checkpoints will be released at https://andrea25512.github.io/CRISP/.
Read the full abstract ▾
All authors Andrea Ceron, Michael Schmidt, Alvaro Marcos-Ramiro, Sebastian Schmidt, Benjamin Busam
Multiagent Systems
Personalization Matters: Long-Horizon Conversation Agent with User-Centric Information in Online Shopping Interactions
Rena Gao, Yue Dai, Hao Guan et al. (+4 more)
Personalized conversational shopping requires maintaining preference consistency over multi-turn interactions, where users reveal constraints gradually. Existing approaches often rely on static profiles and do not explicitly control long-horizon interaction behavior. We propose a multi-
agent,
multimodal Retrieval-Augmented Generation (RAG) framework that decomposes dialogue state tracking, recommendation
retrieval, preference-aware
reasoning, and response generation, while integrating product metadata, product reviews, image-derived descriptions, and user historical reviews. To evaluate interaction-level quality, we adopt a trajectory-level protocol with four dimensions: Global Preference Consistency, Cumulative Information Synthesis, Interaction Trajectory, and Tone Consistency. On an Amazon Reviews 2023
benchmark,
retrieval-enabled variants outperform a no-RAG baseline on automatic trajectory metrics (average 4.82 vs. 3.74). In a small real-user study ($n{=}5$), the Full variant achieves the highest mean overall rating (4.60 vs. 2.20 for Baseline), providing exploratory evidence that role decomposition plus user-centric
retrieval improves perceived personalization.\footnote{Code and
dataset are available at: https://github.com/RenaGao/Multimodel_RAG_Indexing
Read the full abstract ▾
All authors Rena Gao, Yue Dai, Hao Guan, Shengxiang Gao, Wangyang Wu, Yixin Shen, Jey Han Lau
Computer Vision
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
Machine Learning
From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning
Fengyuan Liu, Yue Wang, Hangxi Guo et al. (+4 more)
Continual learning remains challenging for large
language models, which must enable models to acquire new skills and knowledge without degrading existing capabilities. Existing approaches typically address this challenge by carefully designing how model parameters are updated. In contrast,
prompt optimization avoids costly parameter updates while achieving competitive or even superior performance to reinforcement learning methods such as GRPO on individual knowledge-intensive and
reasoning tasks. This raises a natural question: Can
prompt optimization, as an efficient adaptation approach, be directly applied to continual learning? Our analysis shows that, under sequential task adaptation, it suffers from catastrophic forgetting, while optimized
prompts accumulate rules that overfit to local task distributions. To address these limitations, we propose Evolving Functional REpertoires (EFRE), which replaces a single
prompt with a repertoire of functions that evolves as new tasks arrive: compatible updates refine existing functions, while conflicting updates trigger the emergence of new ones. On a three-task continual-learning stream, EFRE achieves a final average performance 7.50 percentage points higher than GRPO. Moreover, after adaptation to the Bio task, its performance on FinQA decreases by only 1.56 percentage points, compared with 25.10 percentage points for the base
prompt optimization method. We further instantiate EFRE in a minimal
agent system and observe consistent improvements across different backbone models. Overall, these results demonstrate EFRE's strong performance in continual learning for large
language models and highlight its substantial potential for continual learning in advanced
agent systems.
Read the full abstract ▾
All authors Fengyuan Liu, Yue Wang, Hangxi Guo, Fengyuan Liu, Chenxu Wu, Yanguang Liu, Mengnan Du
Computation and Language
SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation
Zhi Rao, Yucheng Zhou, Qianran Sun et al. (+8 more)
Contemporary decoder-only large
language models (LLMs) have demonstrated strong capabilities across a wide range of domains. However, existing pretraining paradigms for gloss-free sign
language translation (SLT) are largely designed around conventional encoder-decoder pretrained
language models, which limits their direct applicability to decoder-only LLMs. To address this limitation, we propose SignRAG, a unified framework combining hierarchical pretraining, target-domain
retrieval augmentation, and
retrieval-aware reinforcement fine-tuning. Hierarchical pretraining first learns linguistically grounded sign representations and then jointly aligns the sign encoder with an LLM, mitigating cross-modal optimization imbalance. For downstream adaptation, SignRAG complements parameter-based fine-tuning with a target-domain
retrieval gallery that provides instance-specific translation cues. To ensure that retrieved contexts are used appropriately, we further introduce
Retrieval Utility-Guided Reinforcement Fine-Tuning (RUG-RFT), which combines translation-quality and
retrieval-utility rewards to encourage beneficial
retrieval use while suppressing harmful reliance. Experiments on multiple SLT
benchmarks establish new state-of-the-art performance. In particular, to the best of our knowledge, SignRAG is the first gloss-free approach to outperform gloss-supervised methods across all reported metrics on CSL-Daily. Our code has been released at \href{https://github.com/shahelaojieraozhi/SignRAG}{GitHub}, together with models of different sizes to support future academic research.
Read the full abstract ▾
All authors Zhi Rao, Yucheng Zhou, Qianran Sun, Yiqing Huang, Longcan Yuan, Jiayi Hou, Chengwen Yao, Lin Cheng, Donghui Sun, Xiaoxin Chen, Jun Wan
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 using the structure but cannot scale to structures of large corpora that cannot 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 navigate 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 6.6–11.4 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
Machine Learning
SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces
Rongxue Li, Meng Yang, Yiru Mao et al. (+6 more)
Spatial coding
agents significantly improve spatial
reasoning in
Multimodal Large
Language Models (MLLMs) by using external tools to generate verified execution traces. However, this paradigm inherently suffers from prohibitive inference-time overhead and external dependencies. In this paper, we explore whether an MLLM can internalize this agentic capability to operate entirely tool-free. We begin with a simple observation: prompting an MLLM with summarized execution traces of a spatial coding
agent naturally unlocks the model's internal spatial Chain-of-Thought (CoT). Motivated by this, we introduce SpatialOPSD, an on-policy self-
distillation framework that internalizes spatial
reasoning into a standalone MLLM by formulating verified
agent traces as privileged information. To mitigate privileged-information leakage during
distillation, we introduce Repetition-Aware
Distillation, which combines repetition masking with unlikelihood regularization. Experiments across multiple
benchmarks demonstrate that self-distilling SpatialOPSD achieves higher average accuracy than SFT and GRPO on both spatial and OOD
datasets, exhibiting superior performance and generalization.
Read the full abstract ▾
All authors Rongxue Li, Meng Yang, Yiru Mao, Yongliang Tao, Lulu Hu, Bin Yang, Zhao Xu, Weihua Luo, Bowen Xu
Computer Vision
FlyMark: Training-Free Invisible Watermarking of 3D Gaussian Splatting via a Fruit Fly Connectome
Ziyuan Luo, Haoliang Li and Renjie Wan
A trained 3D Gaussian Splatting (3DGS) scene ships as a portable parameter array that can be copied, pruned, requantized, or repackaged outside its training pipeline, so ownership evidence is most useful when it lives in the released parameters and remains checkable long after the
embedding tooling is gone. Existing 3DGS watermarks typically tie
embedding or extraction to scene optimization, a learned decoder, or rendered views, so the evidence survives only as long as a second trained artifact does. FlyMark instead writes a keyed message into the parameters a 3DGS file already stores. Its carrier directions are derived from the photoreceptors of a published connectome, a citable versioned artifact that fixes the geometry exhaustively and leaves nothing to tune per scene. A virtual observer reads cone-wise apparent luminance along a scene-normalized orbit from stored centers, colors, and opacities; a keyed dithered quantization-index-modulation code replicates each message bit across these observations; and one sparse bounded least-squares solve realizes the targets through achromatic shifts of existing degree-zero colors under a hard per-channel linear-RGB bound. All geometry and higher-order appearance parameters are preserved bit-identically, and extraction needs only cone queries, rounding, and majority voting. Under a model-domain threat model on synthetic and real scenes, FlyMark attains high clean bit accuracy and visual fidelity while cleanly separating matched from wrong keys.
Read the full abstract ▾
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
Machine Learning
Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data
Hao Mo, Liying Yang, Shumin Yao et al. (+4 more)
Binary
diffusion models typically require many function evaluations (NFEs) to generate high-quality samples, making inference costly. Reducing NFEs without sacrificing sample quality or relying on
distillation or additional training remains challenging. Existing binary
diffusion models define discrete one-step forward paths and derive reverse posteriors accordingly. In low-NFE cross-step sampling, they incorrectly approximate a true multi-step likelihood using a single-step transition, causing severe quality degradation. We propose Bernoulli Flow Models (BFM) to decouple generative dynamics from fixed discrete time steps. Instead of sequential one-step Markov
diffusion chains, BFM defines a unified continuous global Bernoulli probability flow path between data and pure noise and derives analytical closed-form posterior transitions over arbitrary time intervals. Reducing the inference NFE therefore only requires re-evaluating this posterior on the new intervals rather than approximating skipped steps. This removes the structural training-inference mismatch of discrete chains and enables strictly self-consistent low-NFE sampling. Experiments show strong robustness under aggressive NFE reduction: on LSUN Churches 256x256, a 256-step-trained BFM achieves an FID of 9.22 with only 16 sampling steps, while the state-of-the-art discrete baseline degrades to 204.10. BFM also remains competitive with continuous and discrete generative baselines under standard full-step inference. These results establish BFM as a theoretically rigorous, self-consistent, and practical framework for fast binary data generation. Code is available at https://github.com/minimo6666/BFM_NeurIPS2026.
Read the full abstract ▾
All authors Hao Mo, Liying Yang, Shumin Yao, Xinxing Yu, Ajian Liu, Xudong Mao, Yanyan Liang
Sound
SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model
Aviad Dahan, Rajaei Khatib, Yonatan Bitton et al. (+3 more)
A 4D audio-visual scene comprises a
video, the dynamic geometry it depicts, and the sound sources that populate it, each with its own position and trajectory. Rendering such a scene from a novel viewpoint requires that every source be available as an individual waveform, so that it can be localized in the scene and propagated to the observer before the signals are mixed. Joint audio-
video generators can synthesize the
video and its soundtrack, but the soundtrack is emitted as a single audio-mix in which the sources are not individually accessible. We present SepGen, which extends a pretrained audio-
video generator to emit the
video, the mixed soundtrack, and one waveform per captioned source in one joint sampling run. SepGen supports two complementary modes: generation and separation. In generation mode, each source caption specifies what its stem contains. A two-speaker dialogue, for example, comes out as one stem per speaker in the original turn order. In separation mode, the input audio-mix remains clean while the captions specify what to extract, so the model can decompose a recording from a free-text description. We evaluate generation on scenes synthesized from text, and separation on scenes rendered by other generators and on real recordings of
speech, music, and sound effects. Given an audio-mix and captions that carry the spoken lines, SepGen outperforms
language-conditioned separators, most clearly on
speech, and it keeps the lead when the lines are removed from the captions. Code, checkpoints, and
datasets are available at https://sepgen.github.io/
Read the full abstract ▾
All authors Aviad Dahan, Rajaei Khatib, Yonatan Bitton, Idan Szpektor, Lior Wolf, Raja Giryes
Computational Engineering · Cross-listed from quant-ph
When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing
Oishik Kar and Aswath Babu H
Multi-
photon interference is the resource most native to photonic
quantum machine learning, yet experiments on photonic reservoirs have reported advantages, null results, and train-only effects. These outcomes cannot be compared: each measures task-dependent accuracy on different tasks and platforms. Here we resolve the question task-independently through the kernel geometry of
boson-sampling feature maps. Interference redistributes feature variance across roughly twice as many effective dimensions as distinguishable-particle statistics, generating a large
geometric separation between the corresponding kernels. The separation grows superlinearly with indistinguishability, is linear in Hong–Ou–Mandel visibility at small visibility for two to four
photons, and retains approximately 80% of its magnitude at the source quality of current
quantum processors. Under experimental sampling budgets the separation is learnable on adversarially constructed tasks (accuracy advantage +0.22 plus or minus 0.05) and an order of magnitude smaller on natural tasks, gated by kernel–task
alignment. The results reconcile the existing experimental record and supply a pre-experimental protocol: kernel geometry establishes that an interference-specific learning resource exists, and task
alignment determines whether a given task can access it; both are computable before committing significant hardware resources.
Read the full abstract ▾
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
Computer Vision
Adaptive Adversarial Augmentation for Controllable Face Synthesis
Saransh Suri, Shivang Agarwal, Mayank Vatsa et al. (+1 more)
Synthetic data provides a scalable alternative to real-world
datasets for training face recognition models, particularly under challenging conditions such as low resolution, occlusion, and masks. Yet, most approaches lack diversity and fail to generalize effectively. We propose Ensemble Feedback Controllable Synthesis (EFCS), a guided framework that generates diverse and challenging samples while preserving visual realism. EFCS expands distributional variability, often reflected in higher FID and KID scores compared to single-feedback and random synthesis, while maintaining high precision. Recognition models trained on EFCS data consistently outperform baselines across multiple
benchmarks, showing improved generalization to real-world scenarios. Furthermore, we introduce an analytically motivated formulation linking perturbation-induced difficulty, sample utility, and performance degradation, offering principled insights into balancing synthetic data complexity for optimal training. Together, these contributions establish EFCS as an effective and analytically grounded approach for bridging the gap between synthetic and real
datasets.
Read the full abstract ▾
All authors Saransh Suri, Shivang Agarwal, Mayank Vatsa, Richa Singh
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
Computation and Language
AdaptEvo: Learning under Imperfect Supervision through Confidence-Adaptive Training with Knowledge Evolution
AllSpark Team
Rule-governed contextual decision tasks require models to apply specified rules to case-specific context and evidence. Written rules can leave gaps in decision guidance and process evaluation, while reference judgments vary in their support from the rules and evidence. To address these challenges, we introduce AdaptEvo, a framework for learning under imperfect supervision that couples confidence-adaptive policy optimization with evolving decision knowledge and evaluation rubrics. Its Training module uses Confidence-Adaptive GRPO (CA-GRPO) to balance outcome and process rewards according to reference confidence. Its
Evolution module synthesizes reusable decision knowledge from recurring failures across training cases and refines process rubrics to detect overlooked errors. To support empirical evaluation, we construct an industrial
multimodal content moderation
dataset comprising a training set and In-Period and Out-of-Period test sets, with the latter collected under changed rules. Using Qwen3.6-35B-A3B, AdaptEvo achieves 61.9% exact-label accuracy and 72.2% binary decision accuracy on In-Period, exceeding GRPO by 7.5 and 3.7 percentage points, respectively. On Out-of-Period, the policy trained with CA-GRPO retains exact-label accuracy gains over the base model across evaluated checkpoints without injected decision knowledge, while GRPO declines with continued training. CA-GRPO also outperforms the tested fixed reward mixtures on both Out-of-Period metrics.
Read the full abstract ▾
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 ▾
Computation and Language
Deception by Omission: Language Models Knowingly Hide Their Mistakes
Lucas Florin, Amelie Knecht, Ulysse Schaller et al. (+1 more)
Large
language models (LLMs) increasingly act as
agents with little human oversight, so potential mistakes they make can go unnoticed. Users then depend on the model to report what went wrong. An honest model discloses its mistakes, while a deceptive one conceals them. However, it is unclear how current LLMs behave in such situations. In this study, we prefill LLM trajectories with synthetic mistakes. The trajectories resemble real deployments in chat and agentic settings. Models fail to disclose their mistake in 36.4% of chat and 67.1% of agentic rollouts. In 2.4% and 5.3% of rollouts, respectively, they are aware of the mistake in their chain of thought but still deceptively conceal it. Rates vary by model: for instance, Gemini 3.5 Flash knowingly conceals mistakes in up to 19.9% of agentic rollouts. In 11.9% of chat and 51.8% of agentic rollouts, models show no awareness of mistakes, even though they reliably spot them when reviewing the same transcript as an outside observer. Our results show that, as
agents take on more tasks with less oversight, users cannot rely on them to self-report possible mistakes. Developers should instead use independent monitors that review
agent trajectories, or specifically train models to check their past actions and disclose what they find.
Read the full abstract ▾
All authors Lucas Florin, Amelie Knecht, Ulysse Schaller, Thilo Hagendorff
Machine Learning
Sample-Efficient Generative Conformal Prediction
Minxing Zheng and Shixiang Zhu
Generative conformal prediction builds uncertainty sets from samples of a conditional generator, which are efficient only when the samples represent the response distribution well. This can require many samples, each of which can be costly, as in large
diffusion models and scientific simulators, so the sampling budget must be used efficiently. Existing methods draw the same number of samples at every input, wasting samples where the response distribution is simple and undersampling where it is complex, which inflates sets and leaves those inputs under-covered. We propose CASA (Conformal Adaptive Sample Allocation), which characterizes the marginal value of an additional sample and allocates samples across inputs to minimize the expected set size subject to marginal coverage and an average sampling budget. Theoretical analysis shows that adaptive allocation yields smaller sets than a fixed count at the same budget: a missed mode forces a radius that spans the gap between modes, and even oracle radius cannot compensate for it. On synthetic and real tasks, CASA produces substantially smaller sets at the same budget, often improves conditional coverage, and complements existing radius-adaptive methods.
Read the full abstract ▾
Computer Vision
EgoPhys: Estimating Peak Contact Force and Mechanical Work from Egocentric Manipulation Video
Zhuo Dong, Jianhua Yang, Haohao Li et al. (+4 more)
Physically grounded manipulation of articulated objects requires understanding both the maximum forces encountered during contact and the work performed as their parts move. Peak contact force and mechanical work quantify these complementary aspects, but estimating them from
egocentric video is challenging because physical interaction cues are local and indirect. Moreover, peak force is associated with brief contact events, whereas mechanical work depends on force-motion coupling throughout the contact duration. To address these challenges, we propose EgoPhys, an RGB-only framework comprising Contact-Aware Spatial Aggregation (CASA) and Target-Specific Multi-Expert Temporal Routing (TMTR). CASA integrates appearance and geometry features to emphasize interaction-relevant cues, while TMTR models semantic, event, and motion cues with specialized temporal experts and routes them separately for force and work prediction. On the test split from Hoi!
dataset, EgoPhys substantially improves predictions of peak force and mechanical work, achieving MAEs of \(5.205 \pm 0.584\) $N$ and $0.894 \pm 0.081$ $J$, respectively.
Read the full abstract ▾
All authors Zhuo Dong, Jianhua Yang, Haohao Li, Yumeng Zhao, Keji He, Yan Huang, Liang Wang
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