Research

• General in-context learning for embodied agents1 paper raises it · 0 address it

  Improving adaptability of models to new tasks and environments without task-specific fine-tuning is critical for scalable embodied intelligence.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Cost and latency in agentic systems2 papers raise it · 1 addresses it

  High computational and time costs limit practical deployment of agentic systems for real-world tasks.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviewsraises · addresses
• Physical-state verification and failure recovery1 paper raises it · 0 address it

  Robustness to irreversible failures and accurate state tracking are essential for reliable embodied control.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Evidence-grounded multimodal reasoning benchmarks1 paper raises it · 1 addresses it

  Current benchmarks often fail to ensure models use necessary audio-visual evidence, weakening evaluation reliability.

  • EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoningraises · addresses
• Length generalization in sequential state tracking1 paper raises it · 1 addresses it

  Models struggle to maintain performance on problems much longer than their training data, limiting scalability.

  • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses

Named by an AI from these papers' abstracts.

• Training & fine-tuning42+90.9%
• AI safety29+61.1%
• Computer vision29+31.8%
• Evals60+25.0%
• Federated learning46+21.1%
• Code models13+18.2%
• Quantum machine learning24+14.3%
• Image & video generation20+5.3%

• arXiv cs.LGOct 16

  Domain-specific language alignment of multimodal embeddings towards explainable predictions

  Gabrielė Tijūnaitytė, Thijs L. van der Plas, Mohamed-Bachir Belaid, Rob Knapen, Maciej J. Soja +1

  Multimodal data are commonly fused into latent representations that improve downstream task performance but are not interpretable, limiting their application in domains that require explainable model decisions. Vision-language alignment has made image embeddings interpretable through language, but requires vast image-caption training data. However, captioned data are typically not available for multimodal embeddings, as relevant features cannot directly be observed and annotated from embeddings alone. Here, we propose a framework to language-align any embedding space that can be linked to interpretable auxiliary data. Captioning functions convert auxiliary data into partial captions; a soft contrastive loss weights pairs by the similarity of their properties that each caption describes; and a rank-based concept retrieval task evaluates alignment against the auxiliary data rather than the captions. We apply this framework to multimodal Earth embeddings to facilitate explainable predictions for two species distribution modelling tasks: S2BMS and SatBird. AlphaEarth embeddings beat previous state-of-the-art models on 6/7 metrics, while our framework language-aligns domain-specific…

  PDF
• arXiv cs.AIOct 16

  WebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement Learning

  Zijun Dou, Zhen Yang, Xijun Liu, Dongzhuoran Zhou, Aohan Zeng +1

  Real-world frontend development requires agents to compose reproduction, generation, modification, and repair over an evolving application state. Learning a general policy for this process requires translating heterogeneous execution feedback into task-aligned rewards and effective credit assignment across long sequences of interdependent actions. We introduce WebCoder, a general frontend development agent trained with artifact-grounded agentic reinforcement learning. Our key idea is to assess diverse development activities through their effects on a shared executable artifact and its satisfaction of task requirements. We build Webdev-World, an executable environment that integrates code editing, application execution, browser inspection, and on-demand skills while preserving project state across interactions. An independent verifier evaluates the final application against task requirements to provide terminal rewards, while changes in intermediate artifact progress redistribute the resulting rollout advantage across development segments. Context compaction and message-tree sample construction support training on trajectories beyond a single context window while avoiding repeated…

  PDF
• arXiv cs.LGOct 16

  Towards a GraphNARX model for structural dynamics

  George Tsialiamanis, Keith Worden

  The current paper introduces the GraphNARX model, a graph-based nonlinear autoregressive exogenous model for structural dynamics. The model is built to account for the geometry of structures and to model dynamic behaviour as the interaction between elements of the structure. Similar to other types of NARX models, GraphNARX is used for system identification. Nodal attributes of the graph encode past displacements and nodal forces, and the output of the model is the next-timestep displacement. The graph formulation of the model allows it to generalise to structures of different dimensions and degrees of freedom. Moreover, because graph-learning is performed locally between the nodes, the GraphNARX model can also learn to infer displacements of nodes for which data are not available, i.e.\ to perform virtual sensing. The proposed model's performance is evaluated in a system-identification framework and a virtual-sensing framework, and achieves good accuracy and exhibits generalisation capabilities to structures of different sizes.

  PDF
• arXiv cs.CLOct 16

  Disentangling Language Effects on Tool Admission and Post-Retrieval Safety

  Aditya Nawal, Manit Baser, Mohan Gurusamy

  LLM agents increasingly use retrieval tools across languages, yet their safety evaluation remains English-centric. It remains unclear whether language affects tool admission, post-retrieval generation, or both. We independently vary request, retrieved-page, and required response languages in a controlled URL-retrieval setting across ten models and seven languages. We identify Safety Loss through Interlingual Processing (SLIP). Non-English harmful requests increase mean tool admission from 46.9% to 67.4%, with a positive mean change in every model. This pattern also persists in an autonomous retrieval setup across all four models tested in this setting. Requiring answers in the page language increases pooled harmfulness on matched tool calls from 50.3% to 57.4% across four closed-weight models, mainly in Chinese and Hindi. Translating pages alone produces no consistent harm increase in eight models with comparable inference settings. Automated audits show that a non-harmful response may be a genuine safety refusal, a deflection citing language difficulties, or an unusable answer. Harmfulness labels alone cannot distinguish these outcomes. Multilingual safety evaluations should…

  PDF
• arXiv cs.AIOct 16

  Rethinking GRPO for Large Reasoning Model Safety Alignment

  Jiawei Chen, Yi Zhang, Jiawei Du, Zhonghou Lv, Tairan Chen +7

  Large reasoning models (LRMs) exhibit strong reasoning capabilities but remain vulnerable to unsafe outputs. While Group Relative Policy Optimization (GRPO) is widely used for safety alignment, its group-relative optimization may provide insufficient safety-directed learning signals. In this paper, we identify two failure modes: advantage collapse, where homogeneous rollout groups yield vanishing advantages, and unsafe diversification, where unsafe behaviors persist and become increasingly diverse. Our theoretical analysis reveals that behavioral consistency weakens within-group safety contrasts, while entropy regularization can diversify unsafe responses when relative signals vanish. To address these challenges, we propose Beacon, comprising Safety Signal Recovery (SSR) and Safety-Utility Decoupled Alignment (SUDA). SSR combines advantage-guided trajectory filtering and safe reference supervision to recover effective safety learning signals, while SUDA employs category-aware rewards and benign-only KL anchoring to mitigate over-refusal without compromising safety. Experiments across four Qwen3 and DeepSeek-R1-Distill variants and eight benchmarks show that our framework achieves…

  PDF
• arXiv cs.LGOct 16

  Where Latents Belong and How They Flow: Joint Identification of Structural Roles

  Xintong Li, Kun Zhang, Yujia Zheng

  Latent factors in dynamical systems can play different roles across observations and time. For example, an idea in a group meeting may be expressed by only some participants, inherit information from earlier discussions, and shape what is said next. We formalize this notion as the structural role of a latent factor, describing where it is expressed, whether it receives influence from the past, and whether it transmits influence to the future. The main challenge is correspondence, since the three structures may be identified under different permutations, while a structural role is defined only when they are aligned to the same latent coordinate. We show that, under suitable structural and variability conditions, all three roles are jointly identifiable under a common permutation at each time point. Guided by this theory, we develop RoleTrace, a framework that traces structural roles in a shared latent coordinate system. Synthetic experiments validate structural recovery, while experiments on multiparty meetings examine the identified roles in real sequential interactions.

  PDF
• arXiv cs.LGOct 16

  Path to Prior-Data Fitted Relational Models via Learned Latent Multi-table Representations

  Mohammad Sadeq Abolhasani, Viswanath Ganapathy

  Prior-data fitted networks (PFNs) show that pretraining on large populations of synthetic tasks can enable generalization to unseen datasets with little or no downstream fine-tuning. This paradigm is effective for transformer-based tabular and relational foundation models such as RDB-PFN, but remains largely unexplored for graph-based relational models built on message passing. We pretrain the graph-based relational foundation model Griffin on large collections of synthetic relational databases and ask whether curriculum learning, which benefits transformer-based relational learners, also improves message-passing representations. Rather than fine-tune on downstream tasks, we use the pretrained encoder as a general-purpose relational representation learner and pass its latent representations to a frozen in-context predictor (\ticl{}); no component is trained on the target task. On 16 real-world relational classification tasks, evaluated over five seeds against raw-feature and untrained-encoder baselines, a purely synthetic curriculum that begins with schema-guided data and continues with schema-agnostic data gives the strongest frozen in-context performance\rev{, outperforming…

  PDF
• arXiv cs.CLOct 16

  Before Retrieval Begins: Safety and Tool-Use Decisions in LLM Agents

  Aditya Nawal, Manit Baser, Mohan Gurusamy

  Large language models increasingly act as agents that call external tools, yet most tool-safety research examines only what follows a tool call. The prior decision of whether to call the tool remains largely unexamined and can influence downstream safety. Across the seven open-weight models, the unweighted model-average harm rate after admitted harmful requests is 74.5%. To identify what governs this decision, we apply a factorial intervention to the input request. Within our generated construction, neutralizing the requested-operation component produces the largest admission contrast (19 pp). A linear direction estimated from this contrast influences held-out admission in four of seven models; effects on operation-neutralized requests in some models show that it is not an operation-specific mechanism. We then test whether written refusal is behaviorally and representationally coupled to the same decision. Written refusal accompanies 33.6% of admitted harmful calls. Plain-text refusal training reduces unsafe admission in models that retain benign tool use, showing that response-level safety training can transfer to the call decision. Together, these results establish a partial,…

  PDF
• arXiv cs.CLOct 16

  ParetoChat: An LLM-Based Interface for Interactive Multi-Objective Optimization

  Gokhan Ceyhan

  Multi-objective optimization models are often deployed in settings where decision makers (DMs) must balance some conflicting criteria. In practice, however, stakeholders must translate their qualitative preferences between different criteria into numerical weights, priorities, or reference points required by optimization methods, which can be difficult to specify and interpret. This paper proposes \emph{ParetoChat}, an LLM (large language model)-based expert-agent interface for interactive multi-objective optimization. The agent translates natural-language user input into structured scalarization parameters, invokes an optimization system, presents candidate solutions, and iteratively elicits feedback. We describe a multi-agent architecture that separates input processing, multi-criteria decision-making (MCDM) expertise, solution presentation, and feedback processing. We then present a simulation study using an LLM-based DM agent and benchmark ParetoChat against interactive methods implemented in DESDEO, including reference-point and NIMBUS methods. The computational experiments on multi-objective binary knapsack and set-partitioning instances show that ParetoChat can guide the…

  PDF
• arXiv cs.CLOct 16

  Same Person, Different Advice: Auditing LLM Financial Advice with Repeated Risk-Tolerance Responses

  Soovadeep Bakshi, Apurba Bose, Aishwarya Bose, Sandip Nandi

  AI financial advisers set a client's stock allocation largely from one stated-risk question, yet people do not answer it the same way twice: in a national US panel, 41% of households chose a different answer two years later, and in a laboratory retest a third of people moved two or more points on a 0-10 scale after six months. Seven large language models from five providers gave one-turn allocation advice for 800 real household profiles in which only the risk answer changed. The recommended stock share moved by 10 to 16 percentage points on average, and by 24 to 35 when the answer changed, against 0.6 to 4.2 points for the same prompt asked twice; in the laboratory retest the rating alone moved advice by 11 to 18 points. Without any note, the models respond to the answer about as strongly as when told that it is very reliable (less so for the two Claude models). If that instructed response is how each model maps attitude to advice, discounting the answer for its measured reliability, as classical test theory prescribes, would cut the swings by a factor of 2.4 to 3.3. The swing is largest for clients under 40. A note that the answer is noisy steadies some models, but shifts their…

  PDF
• arXiv cs.SEOct 16

  Efficient Program Reduction for Library Fuzzing Harnesses

  Haiying Li, Yunlong Lyu, Peng Chen, Hao Chen

  Library fuzzing harnesses translate generated inputs into API calls. When a complex harness triggers a crash, developers must determine whether the cause is a library defect or invalid harness usage. A smaller reproducer can simplify this investigation, but obtaining one requires repeatedly building and executing modified harnesses and analyzing their crashes, making manual or even automatic minimization time-consuming. Moreover, data-dependent statements prevent the reducer to remove unnecessary code and the heavy stack trace symbolization in libraries also slows down the candidate execution. To address these challenges, we present HarnessMinimizer, a system for efficient minimization of C/C++ library fuzzing harnesses. Its optimized pipeline reuses header analysis and prepared libraries and runtimes to reduce the work required to build and execute each simplified harness during the reduction process. It records and replays input values so that unnecessary input operations can be removed without changing the values supplied to surviving calls. It also uses a fast method to check whether each simplified harness preserves the original crash, avoiding repeated stack trace…

  PDF
• arXiv cs.ROOct 16

  Unifying Embodied Foundation Models via a Model-to-Policy Formulation

  Xinyi Hong, Mingyang Ren

  Vision-language-action (VLA) models and world-action models (WAMs) have emerged as promising approaches to robot learning and control. These models integrate multimodal perception and action generation, but differ in their architectures, output representations, and learning objectives. In this paper, we present a unified, architecture-agnostic probabilistic formulation for embodied foundation models based on stochastic kernels. Our formulation has two key components: (i) we characterize embodied foundation models through conditional output distributions and action-realization kernels, which together induce task-conditioned robot policies; and (ii) we connect pretraining and post-training to policy deployment, accommodating model-specific pretraining objectives and offline or online post-training strategies. We instantiate the formulation for OpenVLA and DreamZero, covering autoregressive action-token prediction and joint video-action generation.

  PDF
• arXiv cs.AIOct 16

  Agentic In-Context Learning: What Algorithms Can Transformers Learn in Closed-Loop Interaction?

  Shiguang Wu, Yaqing Wang, Quanming Yao

  The learning algorithm view of in-context learning (ICL) studies how fixed-parameter Transformers learn from supplied examples. Language model agents extend this setting through interaction: their actions determine what evidence enters context next. We call this regime Agentic In-Context Learning (Agentic ICL). Existing studies largely depend on externally supplied contexts or reward-bearing interaction histories, while work on general tool-using agents lacks a learning algorithm view. We represent an interactive learner by its state, update, and decision rule, covering active learning, bandits, and online reinforcement learning (RL). For expressivity, we construct causal Transformers that approximate these algorithms over a finite horizon, and bound the resulting loss in return. For training, we characterize when optimizing process rewards preserves behavior that maximizes the final outcome. Distillation experiments show that Transformers can learn to execute three representative recursions. We then train models from outcome or process rewards without oracle action or state targets, as in RL post-training. Different rewards yield distinct decision policies. Improving the…

  PDF
• arXiv cs.CVOct 16

  TriFold: Folding irregular 3D Gaussians into structured latents for 3D Scene Generation

  Yun Wang, Chiyu Wang, Fan Jiang, Ziyu Zhu, Zhaoxu Sun +3

  Recent progress in 3D generation has motivated growing interest in compact generative representations of complex 3D scenes. For native 3D Gaussian scenes, however, learning such representations remains challenging due to widely varying primitive counts, nonuniform spatial density, and differences in geometry and appearance even among spatially neighboring primitives. In this work, we introduce TriFold, a native 3D Gaussian VAE that encodes Gaussian scenes into a fixed-layout triplane latent and jointly reconstructs their geometry and appearance. The key insight is to impose structural regularity on the latent space while preserving the spatial adaptivity of the underlying Gaussians. During encoding, we use cell-wise learned queries to aggregate projected Gaussians into multiple slots per cell, reducing the information loss caused by single-feature pooling. During decoding, occupancy prediction identifies active regions, where query-based set prediction and candidate selection reconstruct local Gaussian sets with spatially varying primitive counts. Building on this representation, we train a latent flow-matching model for conditional scene-level 3DGS generation, enabling…

  PDF
• arXiv cs.AIOct 16

  Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RL

  Yibin Huang, Conghui Zhu

  Long-horizon interaction requires agents to make multiple decisions in a changing environment. Outcome-based GRPO lacks fine-grained guidance for intermediate decisions. Recent methods distill completed trajectories into reusable skills and use hindsight-conditioned OPD to provide dense token-level credit. However, skill-induced probability shifts do not necessarily represent reward-aligned credit; especially after an erroneous action changes subsequent interaction states, skill-conditioned supervision may become mismatched with the current state. To address this mismatch, we propose \methodname{}, which routes two complementary hindsight skills according to trajectory outcomes and error boundaries: Positive skills capture successful workflows to reinforce successful trajectories and pre-error decisions, while Negative skills capture failure-specific corrections to target decisive errors. The post-error suffix is optimized exclusively by GRPO, retaining outcome-based learning without extending potentially mismatched hindsight supervision. Extensive experiments demonstrate competitive task performance and support effective fine-grained credit allocation.

  PDF
• arXiv cs.CVOct 16

  SynerGest: Temporal-Spatial Synergistic Gesture Generation for Dyadic Conversations

  Chengxiang Guo, Jian Wang, Lanmiao Liu, Zhan Tang, Junhua Fei +1

  Co-speech gesture generation in dyadic conversations for creating immersive virtual avatars remains highly challenging. Existing models often struggle to balance kinematic stability with rhythmic responsiveness and suffer from semantic entanglement, leading to either generic mean-pose regression or unnatural micro-jitters. To address these challenges, we propose SynerGest, a high-fidelity dyadic gesture generation framework grounded in Contrastive Flow Matching (CFM). Specifically, our CFM objective explicitly penalizes mismatched semantic pairs during training, discouraging spatial shortcuts and over-smoothed predictions while improving conditional semantic alignment. Furthermore, to overcome architectural bottlenecks, we introduce the Impulse-Trend Synergistic Attention (ITSA) module. Grounded in the key insight of decoupling "what moves" from "when it moves," ITSA models sharp, speech-driven rhythmic impulses separately from continuous kinematic trends, supporting precise audio-motion synchronization and global structural stability. Extensive qualitative and quantitative evaluations on two public datasets demonstrate that SynerGest achieves state-of-the-art performance,…

  PDF
• arXiv cs.DCOct 16

  DIFFLET: A Fast Inference Engine for Diffusion Transformer Models on AWS Trainium

  Bin Ma, Min Yu, Vijay Kodamalla, Jialin Liu, Dong Li

  On AWS Trainium2, every component of a diffusion model runs as a program compiled ahead of time for fixed shapes, while pipelines differ across models, prompt lengths across requests, and caching decisions across denoising steps. We present Difflet, a serving engine in which five model pipelines share one compilation backend, joint attention is split across cores by attention head, and a host controller decides at each denoising step whether to run the denoiser or reuse its earlier output. A small probe program computes the caching signal on the device and returns one number per step, and a resident model process keeps every program loaded across requests. Across five image and video model families, fused attention accelerates denoiser steps by 1.2-4.3x over the same framework using PyTorch/XLA attention, and at 32.8k visual tokens it is the only attention that compiles. On four of the five models, resident serving is 1.5-3.4x faster than standalone runs that reload weights from a warm file cache for each generation.

  PDF
• arXiv cs.NEOct 16

  SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks

  Kai Sun, Peibo Duan, Zhanglu Yan, Guowei Zhang, Yongsheng Huang +1

  On neuromorphic chips, spiking neural networks (SNNs) consume far less energy than artificial neural networks (ANNs), but the limited memory of these chips requires low-bit synaptic weights and membrane potentials. Existing post-training quantization (PTQ) methods provide them without retraining and, like those for ANNs, minimize numerical errors such as the mean squared error (MSE). In an SNN, however, a quantization error reaches later layers only through the spikes it flips. We find that errors of equal MSE can cause very different accuracy losses, whereas errors that flip the same fraction of spikes cause the same loss. We therefore propose SpikeQ, a spike-guided PTQ framework. For weights, we select the level of each weight by simulating the downstream neurons and minimizing their spike errors. For membrane potentials, most existing methods quantize the state after the reset, whereas neuromorphic chips compare the threshold with the membrane potential stored at a fixed bit width. We target this pre-fire quantization and build a reset-aware grid that places the threshold on a rounding boundary, so rounding never flips the spike at the current time step. We evaluate SpikeQ on…

  PDF
• arXiv cs.AIOct 16

  Where Does the Performance Go? Understanding and Recovering Performance Regressions in C-to-Rust Translation

  Zhiqiang Yuan, Chong Wang, Zhenhao Zhou, Junwei Liu, Xin Peng

  Rust is increasingly adopted as a memory-safe successor to C, and transpilers such as \crust{} can migrate entire C projects while preserving their behavior. Preserving behavior, however, does not guarantee preserving performance. We study this gap on 20 real-world C projects and their \crust{} translations. On the eight projects used for analysis, the translated Rust is more than 3\% slower than the original C on 12 of 19 operations, by up to 62.2\%. By comparing execution-cost profiles, optimized LLVM IR, and compiler optimization remarks across each C--Rust pair, we trace these slowdowns to nine recurring performance issues, spanning residual runtime work, missed compiler optimizations, and C-style source patterns, and derive an optimization direction for each. We then present \ourtool{}, an LLM-based approach that encodes these issues as reusable optimization rules to recover the performance of translated Rust. \ourtool{} profiles each project to locate hot functions and matches them against rule-specific patterns. The LLM then checks each rule's rewrite preconditions against the project context before rewriting, and a rewrite is kept only if it passes both functional and…

  PDF
• arXiv cs.LGOct 16

  GR-OPD: Group-Relative Sequence Credit for On-Policy Distillation

  Yushu Wang, Renkai Yang, Jingcao Xu, Zili Geng, Haihong Tang +2

  On-policy distillation (OPD) provides token-level teacher feedback, yet common sampled-token updates assign credit locally and omit the effects of earlier actions on subsequent feedback. We introduce \method{} (Group-Relative On-Policy Distillation), which decouples feedback computation from credit assignment by aggregating token feedback into calibrated sequence-level credit. We establish a theoretical basis for this approach by showing that, under ideal on-policy assumptions, broadcasting raw summed feedback to every response token yields an unbiased estimate of the negative gradient of the sequence-level reverse-KL objective. To support effective learning in practice, \method{} discounts later feedback that may become less reliable under distribution shift and uses same-prompt rollout groups to calibrate teacher guidance. It preserves relative response preferences while retaining a controlled fraction of the group mean, which we term collective teacher pressure. Across five Qwen3 teacher--student settings and six mathematical reasoning benchmarks, \method{} outperforms vanilla OPD in macro Avg@K in every setting, including gains of 10.9 and 11.5 percentage points in two…

  PDF