TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

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

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems across fields

Open problems for this view are being prepared; they appear within a day.

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksFor AI agentsAPI
Fields · this week
All fields1810Multimodal305Frontier LLMs231Recursive self improvement201Inference & serving148Agents & indirect prompt injection142Robotics126Neural operators124Clinical reasoning114Forecasting time86Linear bandits59Voice AI55Character recognition OCR33Molecular property prediction29AI safety28Federated learning26All 23 fields

Papers

  • arXiv cs.CVImage & video generationSep 25

    PhoenixSR: Generative Heterogeneous Distillation Unleashes Efficient Models for Real-World Super-Resolution

    Xin Di, Mingyu Shi, Yuanfei Bao, Long Peng, Yue Zhao +5

    Real-world image super-resolution (SR) requires recovering perceptually realistic high-resolution images from complex low-resolution observations while preserving faithful content. Diffusion-based SR benefits from strong generative priors but incurs substantial computational overhead, whereas feed-forward CNN and Transformer SR models are efficient yet often struggle to recover realistic high-frequency details. This motivates a natural question: can diffusion priors be transferred to existing diffusion-free SR networks without introducing diffusion components at inference time? To this end, we propose PhoenixSR, a generative heterogeneous distillation framework that transfers diffusion priors to independently designed feed-forward SR networks through score-based distribution matching. Rather than aligning heterogeneous features or imitating sampled diffusion outputs, PhoenixSR uses the pretrained diffusion model as distribution-level supervision, while paired SR supervision preserves reconstruction fidelity. To make distribution matching effective for fidelity-sensitive SR, we introduce Heterogeneous Distribution Adaptation, which adapts the target score to the SR domain,…

    AI70PDF
  • arXiv cs.CVSep 25

    Self-Supervised Perceptually Interpretable Monocular Depth Estimation

    Zain Ul Abidin, George Dimas, Dimitris K. Iakovidis

    Self-supervised monocular depth estimation (MDE) enables depth prediction from monocular images without requiring ground-truth supervision, making it attractive for large-scale and real-world applications. Despite steady improvements in accuracy, most existing methods remain difficult to interpret, as depth is inferred from RGB representations that obscure the impact of individual perceptual image components. This lack of transparency limits systematic analysis of failure cases and reduces confidence in safety-critical settings. This paper presents a self-supervised framework for perceptually interpretable monocular depth estimation (PIMDE), designed to associate depth predictions with distinct perceptual components of the input image. Rather than operating directly on RGB inputs, the proposed method decomposes each image into a set of perceptual feature maps (PFMs), each encoding a specific visual cue. Distinct depth estimation branches process these PFMs independently to produce depth estimates (PIDEs), which are subsequently combined through an explicit fusion strategy. This formulation allows us to examine directly the contribution of each perceptual cue to the final depth…

    PDF
  • arXiv cs.CLSep 25

    Evaluating Sycophancy in Chinese Large Language Models on Factual Questions Derived from Online Search Queries

    Geng Liu, Feng Li, Mengxiao Zhu, Francesco Pierri

    As large language models increasingly mediate information access, factually accurate and independent answers are critical. However, these models can exhibit sycophancy by aligning their responses with users' stated beliefs even when those beliefs are incorrect, potentially presenting misinformation as independently verified and reinforcing users' confidence in false claims. Prior work leaves unresolved whether introducing user beliefs causes correct responses to become incorrect or uncertain, or causes uncertain responses to become belief-aligned incorrect answers. It also remains unclear whether anti-sycophancy interventions preserve or restore factual accuracy or merely shift responses toward uncertainty. We analyze factual sycophancy in Chinese-language information seeking using yes/no fact-checking questions. Our analysis covers 364,941 responses from three frontier Chinese-based LLMs (DeepSeek, Qwen, and Doubao) to 12,165 factual questions derived from real-world Chinese search queries. We evaluate the models with and without reasoning across baseline, belief-conditioned, and anti-sycophancy prompting, tracing matched shifts among correct, incorrect, and uncertain responses.…

    PDF
  • arXiv cs.CLSep 25

    THA: Weighted Finite-State Text Normalization and Inverse Text Normalization for Khmer

    Seanghay Yath

    Text-to-speech needs written text in spoken form, and speech recognition output needs the reverse. For Khmer, neither direction has a maintained open-source tool, and the script makes both harder: words are not separated by spaces, and number words occur inside ordinary words. We present Tha, a Khmer text normalization and inverse text normalization toolkit built from weighted finite-state transducers. It segments and classifies a whole line in one shortest-path search, and a second transducer rejects token boundaries inside a Khmer syllable. On Google's Khmer test suite, Tha agrees with the reference on all 274 cardinals up to one spelling variant, and on 2,906 real TTS prompts, 153 of the 158 sentences it rewrites are correct. Tha is open source under the Apache 2.0 license.

    PDF
  • arXiv cs.CVSep 25

    FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators

    Kai Yao, Marc Juarez

    Modern AI image generators are increasingly deployed as opaque APIs, where customers can query the deployed service, but cannot inspect model weights or architecture. This creates a practical challenge: a provider may pass governance certification with one generator and later silently switch to a cheaper and lower-quality one for deployment, compromising public trust or even safety in high-stakes domains. We study integrity auditing at deployment time and propose FARE (Forensic Acceptance Region Estimation). A certified generator is enrolled by training FARE on images sampled from that generator. After deployment, FARE can determine whether a generated image is consistent with the enrolled generator---using only that image. FARE's features are based on image generator-specific artifacts that have been proposed for forensic applications. FARE amplifies these features during training by finding hard samples that tighten the acceptance region and increase sensitivity to subtle changes in the certified generator. Across generator swaps, including substitutions with similar model versions and model variants, FARE is effective at detecting swaps, consistently outperforming existing…

    PDF
  • arXiv cs.CVSep 25

    STORM-Bench: Evaluating Online Video QA under Evolving and Incomplete Evidence

    Siru Zhong, Shenghan Tan, Rihong Yan, Xiaohui Lv, Yuzheng Zhuang +4

    Reliable online video question answering requires tracking state transitions while selectively abstaining when visual evidence is insufficient. Existing benchmarks focus on static recognition or long-range retrieval, rarely evaluating these coupled capabilities under evolving and incomplete evidence. We present STORM-Bench, comprising 5,736 questions across 630 compact, change-dense episodes spanning five egocentric domains (STORM-Real) and two controlled simulation subsets (STORM-Sim) at 1 FPS. Questions are stratified by a proxy for accumulated change intensity (Low, Medium, High) and query-time answerability (Known, Uncertain). To measure reliability, we introduce STORM-BR, a harmonic metric over joint answer-status correctness that exposes abstention failures masked by aggregate accuracy, alongside STORM-BR-ATTR for uncertainty attribution. Across 14 video LLMs, online accuracy peaks at 60.3\% (mean 51.7\%), whereas STORM-BR ranges from 5.7\% to 35.6\% (mean 18.8\%), driven by pervasive overconfidence on uncertain queries. STORM-Bench shows that task accuracy masks these gaps in epistemic reliability and state tracking. Benchmark and code are available at…

    PDF
  • arXiv cs.CRSep 25

    FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models

    Haoyang Li, Ruoxi Sun, Qingqing Ye, Benjamin Zi Hao Zhao, Yaxin Xiao +2

    Text-to-image diffusion models enable data-efficient "mimicry" attacks, wherein adversaries fine-tune the model on a handful of public photos to synthesize convincing forgeries of a target individual. A common countermeasure is to embed imperceptible, low-energy watermarks, yet recent studies show these signatures are brittle: modest post-processing or lightweight adversarial perturbations readily suppress detection, exposing a fundamental tension between imperceptibility and robustness. We introduce FeatMark, a watermarking framework that shifts from pixel-level, energy-starved perturbations to inconspicuous semantic features: small, scene-consistent micro-features that remain natural to humans while providing a stronger, machine-verifiable provenance signal. FeatMark builds domain-specific feature banks that encode each watermark as a compact concept program, pairing open-vocabulary semantic cues with reliable edit regions and instruction templates. It then automatically selects features that are both feasible and executable and injects them through modular, mask-guided concept editing, yielding highly localized, scene-consistent micro-edits that are difficult to perceive. We…

    PDF
  • arXiv cs.CVSep 25

    CCRV-Bench: Constraint-Based Evaluation of Causal Reasoning in Vision-Language Models

    Linyuan Gao, Yuan Wu, Yi Chang

    Vision-language models (VLMs) have demonstrated excellent performance in visual tasks, but their visual causal reasoning capabilities still lack reliable evaluation. Existing evaluations struggle to distinguish whether a model is performing causal reasoning based on visual evidence or relying on statistical correlations for shortcut learning, thereby potentially overestimating their actual capabilities. This paper proposes CCRV-Bench, a constraint-driven visual causal reasoning benchmark for single-image physical scenarios. We construct an orthogonal framework that evaluates four causal task dimensions: causal relation discovery, state prediction, causal diagnosis, and intervention-outcome prediction. We further introduce entity symbolization, spatial grounding, the factual adversarial constraint, and minimalist output constraints to reduce shortcut cues while preserving the physical commonsense required by the task. Experiments across 14 multimodal models show that constraint sensitivity is task- and model-dependent: intervention-outcome prediction has the largest average effective degradation among the four causal tasks, spatial grounding is the most damaging constraint on…

    PDF
  • arXiv cs.LGSep 25

    Does Uniform Discrete Diffusion Need Time?

    Chunsan Hong, Chieh-Hsin Lai, Satoshi Hayakawa, Yuhta Takida, Jong Chul Ye +1

    Uniform discrete diffusion models (UDMs) commonly use explicit time conditioning, but we find that it can often be unnecessary in practice. In this paper, we first show that the population-optimal UDM predictor generally depends on time: time controls how much the model should trust the observed context. We then show that this dependence can become negligible in finite-data settings relevant to language. When a corrupted training sequence remains much closer to its original clean sequence than to competing training sequences, the empirical-optimal predictor is nearly insensitive to time over most of the diffusion trajectory, where the guarantee weakens toward the high-noise endpoint. Empirically, trained language UDMs exhibit limited time sensitivity over most of the trajectory, while time-agnostic predictors remain competitive with, and often outperform, time-conditioned models across datasets and training objectives. These results challenge the use of explicit time conditioning in UDMs: although the population optimum depends on time, explicitly conditioning on it may often be unnecessary in practice.

    PDF
  • arXiv cs.LGSep 25

    A Mesoscopic View of Transformer Weights Through Row and Column Scale Fields

    Tiexin Ding

    Pooled statistics of Transformer weights obscure how magnitude is distributed across functional channels, while individual weights are too numerous to compare directly. We study the mesoscopic level between them: row and column scale fields, the median-centred log-RMS profiles of a weight matrix over its channels, which together with a global scale and a full balanced core represent the matrix exactly. Across public Pythia checkpoints at four sizes and controlled runs from three initialization families, balancing reveals similar measured core magnitude profiles. A mixture bridge, with its form fixed before the analysis and its coefficients fitted, predicts the pooled-shape departure from field width on held-out runs and data arms of the controlled grid. The indexed fields retain further structure: they align across projections that share a functional channel, and query/key profiles follow reassigned RoPE frequencies rather than fixed matrix coordinates. Training trajectories show early field formation followed by component-dependent broadening or recession. Extending the channel-based analysis to AdamW's second moment reveals related functional organization in its log-space row…

    PDF
  • arXiv eess.ASSep 25

    A Comprehensive Study of Content Representations for Speech Synthesis

    Diego Torres, Axel Roebel, Nicolas Obin

    Speech content representations are central to voice conversion, speech-to-speech translation, and multimodal language models, yet they are rarely compared under a common generative framework that directly measures what each representation contains. We address this by training a generative model conditioned solely on each representation and evaluating the generated audio along the content, speaker identity, and prosody axes. Across SSL features, supervised tokens, posteriorgrams, and neural audio codecs, we find two distinct regimes: representations that nearly reconstruct the original audio, and representations that effectively disentangle speaker identity. These results show that disentanglement depends not on supervision alone, but on the interaction between the training objective and the representation's information capacity: supervised representations only disentangle speaker identity when their capacity is sufficiently constrained.

    PDF
  • arXiv cs.CLSep 25

    Coupled Usage-Sense Processes: Temporal and Attributable Lexical Semantic Change

    Haruka Ezoe, Ryohei Hisano

    Lexical semantic change is usually summarized by a scalar distance between independently sampled period distributions. This measures how much a word changed, but does not reveal when it changed, which mechanisms and component movements carried the change, or which usages support the attribution. We introduce Coupled Usage--Sense Processes (CUSP), which derives these answers from a single marginal preserving temporal process. A hierarchical coupling relates contextual distributions through latent usage components, while Markov composition makes adjacent and longer span correspondences compatible. Displacement operators quantify change magnitude and timing, split variation exactly between movement of component centers and reorganization within components, and attribute it to transported component pairs. Word-local modes resolve distinct directions of change and their activity over time, while representative passages from attributed components ground the analysis in text. Under a Gaussian mixture specialization, we prove parametric recovery of the operators and squared distances. Synthetic experiments support the predicted rate. CUSP remains competitive on English and German DWUG…

    PDF
  • arXiv cs.LGSep 25

    LipSSM: Structurally Lipschitz-Bounded Cascaded State-Space Model via Metric Transfer between Consecutive SSM Layers

    Natsuki Yoshino, Ren Uchida, Kazuki Matsumoto, Kohei Yatabe

    Lipschitz continuity is a fundamental principle in the design of certifiably robust deep neural networks (DNNs), wherein adjusting the Lipschitz constant, which quantifies network robustness, is of central theoretical importance. A standard approach to enforcing Lipschitz continuity requires each layer of a DNN to be Lipschitz continuous, thereby guaranteeing overall Lipschitz continuity. However, this layer-wise approach typically imposes overly conservative restrictions by producing a loose estimate of the overall Lipschitz constant, which limits the expressive capacity of the DNN and degrades empirical performance at a prescribed level of robustness. To overcome this loose estimation, the recently proposed LipKernel transfers information across layers to yield a much tighter overall Lipschitz bound than conventional layer-wise construction. In this paper, we extend this concept to cascaded state-space models (SSMs) to construct Lipschitz-continuous DNNs capable of modeling longer-term dependencies. The proposed architecture, named LipSSM, is theoretically justified and empirically evaluated.

    PDF
  • arXiv cs.AISep 25

    Factorized axis convolutional gated recurrent unit with dynamic adaptive pooling for remaining useful life prediction of rolling bearings

    Hanbyeol Park, Jungho Choo, Hyerim Bae

    Convolutional neural networks (CNN) are widely used to predict the remaining useful life (RUL) of rolling bearings from time-frequency representations (TFRs) of vibration signals. However, during degradation, characteristic structures in TFRs align predominantly along the frequency or time axis, making it challenging for conventional CNN isotropic kernels to capture directional structure. Furthermore, global average pooling (GAP) averages across axes, potentially obscuring the locations and concentrations of salient activations. This study introduces a factorized-axis convolutional gated recurrent unit (GRU) that employs multiscale anisotropic convolution and dual-axis convolution block attention module to enhance directional features and highlight salient time-frequency regions. Dynamic adaptive pooling (DAP) adaptively aggregates the time-frequency-axis information from the extracted feature maps, whereas a GRU captures temporal dynamics in the latent representations and Monte Carlo dropout enables predictive uncertainty estimation. Experiments on two public bearing datasets demonstrate that the proposed model outperforms existing RUL prediction methods across operating…

    PDF
  • arXiv cs.AIAgentsSep 25

    SciHorizon-eLab: An Agentic Protocol-to-Task Compiler for Scalable Benchmarking of Scientific Embodied Agents

    Maokai Qin, Chuan Qin, Qi Zhang, Dianyu Liu, Zirui Liu +3

    Embodied agents offer a promising route to automating scientific experimentation, yet their progress is constrained by the lack of reliable and systematic evaluation environments. Existing simulation-based laboratory benchmarks rely heavily on manual task engineering, making it challenging to systematically compile diverse scientific protocols into executable and verifiable embodied tasks at scale. To address this challenge, we introduce SciHorizon-eLab, an agentic protocol-to-task compiler that formulates scientific embodied task construction as a compilation problem. Given a natural-language protocol of scientific experiments, SciHorizon-eLab progressively compiles laboratory protocols into semantic-preserving embodied tasks through semantic grounding, executable task synthesis, and multi-stage simulation-based certification. The system generates semantically grounded environments, executable manipulation programs, and step-level success specifications, while enabling reproducible generation of expert demonstrations and execution traces. Using this pipeline, we further construct \BenchName, a ready-to-use benchmark comprising 300 certified tasks across diverse laboratory…

    AIRoboticsEvals80PDF
  • arXiv cs.CLSep 25

    FAVoR: Measuring and Mitigating Author-Style Homogenization in Federated Personalized Generation

    Lu Han, Jingyao Zhang, Katy Ilonka Gero, Nguyen H. Tran

    Large language models are increasingly used as personalized writing assistants, but adapting a model across many authors can compromise individual writing style by pulling author-specific signals toward a shared register. Federated parameter-efficient fine-tuning (PEFT) offers a data-local setting for this multi-author adaptation problem: clients keep author text local while sharing compact adapter updates. However, we show that standard aggregation can preserve continuation utility while making different authors' generations less distinguishable in style space, a failure mode we define as author-style homogenization. We evaluate author-style retention with Angular Style Classification Encoder (ASCE)-based diagnostics on our main BlogText benchmark and ASCE-independent external authorship verification. Using this protocol, we find that common federated PEFT baselines can preserve semantic utility while averaging out author-specific signals. To address this homogenization, we instantiate FAVoR (Federated Authorial Voice Retention), an author-style residual mechanism for federated PEFT. FAVoR uses a shared-private adapter design: clients upload shared-adapter updates while…

    PDF
  • arXiv cs.AISep 25

    MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens

    Subhojyoti Mukherjee, Md Mehrab Tanjim

    Most work on improving large language models treats accuracy as the sole objective. We argue that the harness, the Python code surrounding the model that constructs prompts, routes calls, and parses outputs, is a first-class design surface whose quality is inherently multi-objective: an accurate harness that refuses no unsafe request, or that consumes an order of magnitude more tokens, is not a good harness. We present Meta-Harness, a system that casts harness design as search over three per-domain objectives (accuracy, behavioural safety, and token cost) solved by an agentic proposer (Claude Code) with full filesystem access to prior harness source, execution traces, and scoring artifacts. Our central finding is that a singlephase joint-reward proposer (MoMHa) outperforms every alternative, including a two-phase "accuracy then tokens" ablation, scalar-only feedback, and an accuracy-only baseline. We evaluate on seventeen domains: seven synthetic capability suites, seven real-world public benchmarks (HumanEval, MBPP, Spider, FEVER, MMLU-Pro, LawBench, NuminaMath), and three U-SafeBench-derived user-specific safety domains, using a 12-model fleet spanning four families. On the…

    PDF
  • arXiv cs.LGSep 25

    Gradient Surgery for Physics-Informed Neural Networks

    Thomas Borsani, Giuseppe Di Fatta

    Physics-Informed Neural Networks (PINNs) are trained by optimising a composite objective that combines data fitting with physics-based constraints, typically resulting in a highly imbalanced multi-task optimisation problem. Under these conditions, existing optimisation strategies are affected by conflicting task gradients, leading to slow convergence and unstable training, particularly for stiff and high-frequency partial differential equations. We analyse gradient conflicts throughout training of PINNs with standard optimiser and investigate Multi-Task Deep Learning (MTDL) optimisation methods. In our analysis across four benchmark problems we observed that PINN optimisation exhibits three distinct phases in which angle- and magnitude-based gradient conflicts alternate, with only one present at a time. Building on these observations, we propose PAM-GS, a physics-aware gradient surgery method that adaptively mitigates task interference during training according to the observed conflict types. Experiments on four representative PDE benchmarks demonstrate that PAM-GS combines competitive solution accuracy with consistently strong task-balanced performance, outperforming existing…

    PDF
  • arXiv cs.CVSep 25

    Where and When to Force: Routed Forcing for Streaming Avatars

    Zihan Su, Siwen Lu, Junhao Zhuang, Zeyue Xue, Haoyang Huang +4

    Audio-driven streaming avatar generation requires real-time synthesis of speech-synchronized videos with dynamic and diverse motion. Self Forcing uses Distribution Matching Distillation (DMD) to distill bidirectional video diffusion models into causal, few-step generators for real-time streaming. However, DMD minimizes a reverse KL divergence, which is inherently mode-seeking: it causes the student to discard high-dynamic modes and collapse onto static outputs, compressing both dynamics and diversity of generated videos. We find that this collapse is region-heterogeneous: person regions involving pose and gesture variations suffer the largest diversity loss, the audio-driven mouth region shows a small loss, and the background remains nearly stable. Based on this observation, we propose Routed Forcing, which routes the distillation objective by semantic region and noise stage to improve dynamics and diversity while preserving visual quality. Specifically, (1) Where to Force: Semantic-Region Routing applies Data-Forcing Distillation (DFD), which supervises the student with real videos, to the person region where diversity collapse is most severe, while retaining DMD for the mouth…

    PDF
  • arXiv cs.CVSep 25

    IDM-Net: A Lightweight Illumination-Decoupled Modulation Network for Low-Light Image Enhancement

    Cheng-Yen Hsiao, Jing-Ming Guo

    Low-light image enhancement (LLIE) remains challenging for lightweight models because illumination restoration and color fidelity are difficult to optimize simultaneously in the RGB color space. Although recent color-decoupled methods separate luminance and chrominance representations, they primarily optimize luminance as an enhancement target, leaving its potential as an explicit guidance prior largely unexplored during feature reconstruction. To address this limitation, we propose IDM-Net, a lightweight Illumination-Decoupled Modulation Network for low-light image enhancement. IDM-Net adopts a dual-encoder architecture consisting of a structure encoder that extracts multi-scale appearance features from the RGB image and a lightweight illumination encoder that learns illumination priors from the decoupled luminance (Y) channel. To effectively exploit these priors, we introduce an Illumination-Guided Modulation (IGM) module that injects multi-scale illumination cues into the decoder through spatially adaptive affine modulation, enabling accurate brightness restoration while preserving natural color consistency. Furthermore, we design a lightweight Feature Refinement Block (FRB)…

    PDF
Load more

Rising research topics

  • Diffusion priors190.0%
  • Character recognition OCR33−13.2%
  • Voice AI55−17.9%
  • Algorithmic fairness7−22.2%
  • Quantum machine learning22−26.7%
  • Channel state information13−27.8%
  • Recursive self improvement201−38.2%
  • Forecasting time86−40.7%