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

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI
Fields · this week
All fields3448Multimodal553Agents534Frontier LLMs463Inference & serving280Image segmentation191Graph learning173Learning verifiable rewards1673D scene164Voice AI103Classifier & causal discovery91Forecasting time85Flow matching75Evals60Teacher policy distillation54Federated learning51All 32 fields

Open problems across fields

  • 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.

Rising research topics

  • Training & fine-tuning42+90.9%
  • AI safety29+61.1%
  • Quantum machine learning29+38.1%
  • Federated learning51+34.2%
  • Computer vision29+31.8%
  • Evals60+25.0%
  • Code models13+18.2%
  • Image & video generation20+5.3%

Papers

  • arXiv cs.CLOct 15

    Thunder-DeID+: Boundary-Aware Korean De-identification from Court Judgments to Broader Sensitive Documents

    Gyuseong Lee, Gyeongje Cho, Jongmin Kim, Heejin Kim, Yeonkyoung So +6

    This study examines the transferability of a de-identification model developed for Korean court judgments to a broader range of sensitive documents, focusing on boundary precision, label granularity, and recall. The agglutinative structure of Korean causes Byte Pair Encoding (BPE) tokenizers to frequently merge Personally Identifiable Information (PII) with adjacent particles, which complicates accurate span recovery. Furthermore, current PII taxonomies lack sufficient granularity for legal texts. To address these issues, this study introduces Thunder-DeID+, which integrates a refined three-tier PII taxonomy with a boundary-aware tokenizer. The tokenizer enhances a pretrained BPE vocabulary by incorporating N-gram and boundary-scoring components to better align token and PII span boundaries. The proposed approach is evaluated using a tokenizer-independent word-segment-level protocol. On full-length judgments, the tokenizer consistently improves W. Strict Typed F1-score from 0.76-0.77 to 0.87-0.88 across four model sizes (150M, 395M, 750M, and 1B), mainly by increasing precision rather than model scale. With fine-tuning on 1,000 broader sensitive documents, the judgment-trained…

    PDF
  • arXiv cs.CLOct 15▲ 3

    TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents

    Aaron J. Li, Weijia Xu, Chandan Singh, Zixiao Chen, Jeevana Priya Inala +6

    Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering. Their token efficiency is typically evaluated on isolated tasks, whereas real-world developers use them to continuously build, update, and maintain large-scale projects. This mismatch motivates us to evaluate agents over sequences of realistic coding tasks, where we find that agents exhibit recurring environment-dependent token costs that existing methods struggle to reduce. To minimize these costs, we introduce TokenEconomizer, an external controller that cuts environment-specific token costs over a sequence of tasks. These cuts come from determining (i) which operational micro-skills to inject, (ii) which persistently irrelevant tools to prune, and (iii) when to intervene in unproductive failure loops. Across Claude Code, Codex, and GitHub Copilot CLI paired with frontier models, TokenEconomizer reduces the average token cost by 18.4-30.9% with comparable task success. Savings hold in every repository under every tested agent-model setting and generalize to diverse domains such as sequential web development and security auditing, where costs fall by 6.4-21.2% depending…

    Code
  • arXiv cs.LGOct 15

    OrderFlowDiT: Transport-Regularized Diffusion Transformer for Probabilistic Limit-Order Supply Forecasting

    Jung Hun Phee, Tucker Balch

    We study the conditional distribution of limit-order volume submitted over the next five minutes, given the current order book and recent order flow. The task requires capturing price placement, total volume, and predictive uncertainty jointly. Coordinate-wise diffusion losses do not explicitly account for price displacement, while normalizing fields to unit mass removes information about total volume. Agreement on selected summary statistics also does not establish fidelity to the joint field distribution. We introduce OrderFlowDiT, a conditional Diffusion Transformer for unnormalized bid and ask volume-at-price fields, trained with an unbalanced optimal-transport (UOT) auxiliary loss. We also develop a full-field evaluation framework that combines a transport cost sensitive to price placement and total volume with proper scoring rules and calibration diagnostics. In the primary comparison on 1950 validation conditions across 30 U.S. equities, adding UOT reduces full-field transport cost by 45.8% and the transport energy score by 26.1% relative to training with mean squared error alone. Both measures improve for every stock. These findings support incorporating price geometry…

    PDF
  • arXiv cs.CVOct 15

    Improving OCR Accuracy Through Multi-Classifier Verification of Visually Similar Characters

    Nuzhat Khan, Ab Al-Hadi Ab Rahman, Mohamad Anuar Kamaruddin, Muhammad Paend Bakht, Sana Fatima +2

    Distinguishing visually similar characters is a persistent challenge for optical character recognition (OCR) systems, causing errors in critical applications of text digitization. While preprocessing techniques improve image quality and word-level post-processing corrects spelling errors, neither addresses character-level visual ambiguity, an intrinsic property of certain character pairs that limits even state-of-the-art OCR models. We present the Character Verification Model (CVM), a character-level post-processing framework that verifies and corrects ambiguous characters in OCR outputs using specialized binary classifiers trained on visually confusable pairs such as 'O'/'0', 'Z'/'2', and 'S'/'5'. CVM operates independently of dictionary validation, making it suitable for non-lexical data including serial numbers, alphanumeric codes, and license plates. Experiments on three OCR engines (Tesseract, EasyOCR, TrOCR) and ten fonts with low to high complexity demonstrate accuracy improvements of 3.95-14.81 percentage points, with an 87.3% correction rate for visually similar character errors and a false-correction rate of only 2.3%. The modular architecture integrates with existing…

    PDF
  • arXiv cs.CYOct 15

    A misinformation playbook sharpens judgement without breeding cynicism

    Tong Guo, Teng Ye, Yutong Xie, Qiaozhu Mei

    Misinformation harms public health and democracy, and generative artificial intelligence now writes falsehoods as persuasive as people's. Defences range from fact-checking individual claims to training people to resist falsehoods. Yet many claims are too new to check, and interventions that teach doubt can reduce belief in truth too. We propose a defence that targets not the facts of each claim but the persuasion strategies that recur across them. Here we show that learning misinformation's persuasion playbook, mapped from 214,646 fact-checked claims in 51 languages, can sharpen human and machine judgement of claims they know little about, without making either more cynical about true claims. The playbook spans social influence, information manipulation and emotional appeals, combined around a core of fear, conspiracy and fabrication. Briefed with it, plus a reminder that persuasion is not proof of falsehood, a language model better distinguished true from machine-generated false claims about events after its training data. In a pre-registered experiment, the same briefing improved people's discernment of claims they reported as unfamiliar and left their belief in true claims…

    PDF
  • arXiv cs.AIOct 15

    LEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs

    Guy Bar-Shalom, Mor Geva, Fabrizio Frasca, Haggai Maron

    Large language models exhibit misbehaviors that hinder deployment in high-stakes settings. One approach to monitor such failures is to use an external LLM as a monitor, but this is prohibitively expensive. A well-known and efficient class of monitors can detect such failures from internal representations (such as activation probes), but are tied to the model they were trained on, requiring costly re-annotation as new LLMs appear. A natural way to avoid this repeated annotation cost is to develop internal-representation based monitors that transfer zero-shot across LLMs. However, such transfer is challenging because internal representations are not naturally aligned across models; in particular, attention maps, known to contain signals of misbehavior, may differ in head function, ordering, and model depth. In this work, we characterize those cross-model attention mismatches as algebraic symmetries and use geometric deep learning principles to build LEMON (Language-model Equivariant MOnitoring Network) an online graph neural network-based monitor, whose predictions are invariant under these symmetries. LEMON processes attention maps token-by-token, as they are produced and outputs…

    PDF
  • arXiv cs.CROct 15

    The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems

    Georgios Politis, Evangelos Pappas

    Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconstruct text from these messages. Comparing privacy evaluations is difficult when attackers see different messages, know different model weights or use different datasets and recovery measures. We present LLM-Attacker, a framework that records these choices and lets researchers check, compare and extend an evaluation. Compatible attacks reuse recorded messages, and their predictions are saved for independent scoring. The scoring rule requires a linked undefended reference before a defence can pass. Reports also identify attacks that remain untested. In a controlled GPT-2 experiment, adding gradients returned during training increased token recovery from 94.20% to 97.38% and exact-document recovery from 13.71% to 37.77%. The 95% interval for the token gain lay above the two-percentage-point threshold fixed before testing. This experiment is shared with a companion study; here, it tests how the evaluation responds to a change in attacker access. Further studies measure how corpus choice and compression defences affect recovery, compare an adapted published attack…

    PDF
  • arXiv cs.CLOct 15

    CoLU: Confidence-Weighted Layerwise Unlearning for Large Language Models

    Jingkai Guo, Ziyi Zhao, Chaitali Chakrabarti, Deliang Fan

    Large language model (LLM) unlearning aims to forget certain information while preserving others, without retraining from scratch. SoTA methods such as NPO, SimNPO, and SatImp balance forgetting and retain through whole model fine-tuning, while FOM-UL explores selective layer updates. Prior works show that suppressing target information can damage retained knowledge. This trade-off can vary across layers even under the same unlearning loss. In this work, we propose Confidence-Weighted Layerwise Unlearning (CoLU), which combines a novel confidence-weighted forgetting and retain regularization while updating a single selected transformer layer, rather than the whole model for unlearning. To reduce CoLU compute cost, we further propose Brief Layer Screening (BLS), which uses a newly defined normalized forgetting-retention (NFR) score to first rank layers through a brief unlearning trials using a subset of forgetting dataset and fewer epochs. BLS pre-selects top-k ranked layer candidates, which will then be fully profiled using full data analysis. BLS is proven to reduce the runtime of CoLU by 60.2-79.7% with almost the same performance. On TOFU dataset, CoLU improves both forgetting…

    PDF
  • arXiv cs.CVOct 15

    HilbertGen-3D:Hilbert--Multifractal Conditioning for Topology-Aware 3D Generation

    Ziyi Zhang, Shixuan Li, Yorie Nakahira, Paul Bogdan, Guannan Qu

    High-fidelity 3D generative modeling underpins game asset creation, medical imaging, and VR/AR environmental design, where geometric structure directly influences perception and decision-making. Diffusion models represent a powerful paradigm for point cloud generation. However, existing approaches rely heavily on local voxel or patch features and often miss global structural organization, and much less work has studied how global conditioning can be used to improve generation quality. In this paper, we introduce HilbertGen-3D, a novel topology-aware conditional diffusion framework based on Hilbert-Multifractal Conditioning (HMC). HMC computes multi-scale voxel measures, serializes them via a 3D Hilbert curve to expose structured spatial dependencies, and estimates the generalized fractal dimensions from scale-dependent partition functions. We encode these signals as global embeddings and multi-scale tokens, and inject them into a diffusion denoiser through an efficient bottleneck fusion module. Across the Chair, Airplane, and Car categories of ShapeNet, our two conditioning variants reduce the absolute deviation of 1-Nearest Neighbor Accuracy (1-NNA) from 50% by up to 8.90…

    PDF
  • arXiv cs.CLOct 15

    ARBOR: Locating Reasoning Failures in Long Chains of Thought through Reasoning State Tracking

    Huihan Li, Siyuan Wang, Naga Vamsi Ramana Dinavahi, Xiaohui Liu, Xiang Ren

    Large reasoning models solve complex problems through long chains of thought, in which prior work has documented failure modes such as overthinking, underthinking, and unsupported deductions. Existing methods detect these failures from local signals: textual similarity to nearby steps, switch tokens, or an LLM's judgment of a step's correctness. However, what a step contributes to the solution depends on the state that earlier steps have established, so identifying failures requires a global view that tracks that state across the trajectory. Therefore, we propose ARBOR, a reasoning-failure attribution framework that represents each trajectory as a tree of reasoning states, built as each step creates, verifies, prunes, or revisits a state, and attributes each failure to a relation between a step and the state preceding it. Using ARBOR, we refine the three failure modes into distinct subtypes that harm reasoning through different mechanisms and at different costs. We find that the tree state ARBOR maintains before a step separates failure steps from the at-risk steps at which the failure did not occur. We discuss how ARBOR integrates with existing mitigations at inference time and…

    PDF
  • arXiv cs.ROOct 15

    ChairNav: Cross-Embodiment Pre-training and Personalization for Long-Horizon Wheelchair Navigation

    Junhua Huang, Zhizheng Liu, Honglin He, Xiang Zhang, Bolei Zhou

    Developing autonomous electric wheelchairs capable of long-horizon sidewalk navigation is critical for accessible personal mobility, yet existing approaches either focus on indoor map-based navigation or rely on expensive, complex sensor stacks to achieve full autonomy. In this work, we propose to tackle outdoor sidewalk navigation by leveraging visual navigation foundation models and large-scale navigation datasets, which offer strong generalization using lightweight hardware. To this end, we present ChairNav, a novel framework that adapts a general visual navigation model into a personalized electric wheelchair navigation system using a three-stage data pyramid. To address the scarcity of in-domain data, ChairNav first pre-trains on large-scale cross-embodiment datasets transformed into the wheelchair domain, followed by mid-training on a small number of wheelchair demonstrations to eliminate remaining domain gaps. Finally, a post-training stage refines the deployed model from user interventions to personalize its behavior. We deploy ChairNav on a commercial electric wheelchair equipped with an RGB-D camera and an onboard NVIDIA Jetson compute module. Experimental results…

    PDF
  • arXiv cs.HCOct 15

    Risk and Refusal: Mechanisms of LLM Responses to Suicidal Ideation

    Drishti Goel, Soorya Ram Shimgekar, Jeongah Lee, Violeta J. Rodriguez, Daniel S. Brown +2

    Refusal is a common safety mechanism in large language models (LLMs), yet in contexts of suicidal ideation (SI), refusing to engage can itself constitute a safety failure. We evaluate how eight instruction-tuned LLMs respond to SI and self-harm disclosures across three datasets, varying whether models are informed that a disclosure expresses SI and whether they receive a clinician-developed response protocol, and complement this with mechanistic analyses in six open-weight models. Our results reveal a nuanced relationship between refusal and response-level risk. At baseline, elevated risk in model responses is driven primarily by inattention to the disclosure, alongside refusal to engage. Mechanistic analyses suggest that models may refuse SI disclosures through the same direction that mediates their refusals of harmful requests. However, informing models of the SI context, or suppressing refusal directly, increases engagement without reliably lowering response risk, and may raise it. In contrast, the clinician-guided protocol consistently reduces response-level risk while also reducing refusal. Together, these analyses and ablations motivate the need for models that refuse only…

    PDF
  • arXiv cs.CLOct 15▲ 0

    First Passage Attention

    Yuxuan Liu

    Augmenting softmax attention with forget gates typically relies on summing decay contributions along the key--query path. Because such accumulation is monotonic, these mechanisms cannot selectively erase intermediate context while preserving older, structurally relevant tokens. We propose First Passage Attention (FPA), which shifts from path summation to path extrema by lowering a key's logit proportionally to the deepest dip of a learned scalar field below that key's level over the intervening span. FPA encompasses the Forgetting Transformer (FoX) as a special case, and when the field and levels follow a shared learned walk, the alive keys with unpenalised logits naturally form a stack. We show that a constant-dimension FPA head realises any subset of keys left alive by subsequent dips, whereas softmax heads with positional biases or token-level forget gates require a head dimension linear in the number of keys. In synthetic experiments, one-layer FPA heads converge to these target sets while comparable softmax and FoX baselines fail on every seed. Scaling to a 110M-parameter language model, FPA matches FoX in perplexity and uniquely achieves perfect passkey retrieval at…

    Code
  • arXiv cs.LGOct 15

    Spectral Limits of Polynomial Graph Filters on the Long-Range Ising Model Benchmark

    Amin Najafgholizadeh, Mohsen Afsharchi

    The Long-Range Ising Model benchmark (LRIM) guarantees long-range dependence by construction: each label is the node's spin times the spin field convolved with a power-law coupling, so any model's distance from the target is measurable. We prove that a readout whose filter is a polynomial in the adjacency, the linear core of isotropic message passing and spectral graph networks, leaves an error floor that no degree lowers, because the target varies along a level set of the spectrum on which every such filter is constant. Computed exactly, the floor and the best filter of each degree predict two spectral networks adapted from published architectures to within a tenth of a decade. A filter escapes the floor only if it weighs separately the offsets the adjacency lumps together, and must still resolve the coupling across the whole lattice. A strided filter of about fifty coefficients does both: fitted to the training labels, its test error is 52 times below the best published network's. A dilated convolutional network beats the best published result at 256 nodes, matches it at 1,024, and gives the first in-domain results at the three larger sizes, while a Fourier neural operator with…

    PDF
  • arXiv cs.LGOct 15

    Normalizing Flow Maps

    Francesco M. Ruscio, Timothy James Hitge, Fred Zhangzhi Peng, Danyal Rehman, Zander W. Blasingame +4

    Scalable approaches to learning neural dynamical systems have placed diffusion, flow matching, and few-step generators in flow maps at the forefront of generative modeling. Such state-of-the-art models have limited access to explicit model densities despite evolving from classical generative modeling approaches that leveraged tractable likelihoods, e.g., Normalizing Flows and Autoregressive models. In this paper, we combine these threads of few-step generation and tractable sample likelihoods and introduce Normalizing Flow Maps (NFM), a class of exactly invertible pushforward maps that generalizes normalizing flows and flow maps. More precisely, NFMs learn the integrator of an underlying dynamical system, but crucially, they provide efficient exact likelihood evaluation by construction. To enable scalable training of NFMs, we derive two complementary axes of consistency inherent to NFMs that yield (self) distillation objectives: (1) pointwise matching, which unlocks $\ell_2$-based flow-map style regression losses, and (2) distributional matching, which matches pushforward distributions to the marginals of a prescribed forward process. On conditional image generation on CIFAR-10…

    PDF
  • arXiv cs.AIOct 15▲ 7

    GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations

    Nicholas Saban, Charvi Bannur, Mariya Vasileva, Darshan Deshpande

    Text-based world models have recently shown potential to simulate complex RL environment state transitions for a diverse set of use cases. However, no standardized benchmark exists to compare, study and improve these models. Through this paper, we attempt to solve this problem by building GlobeBench, a novel benchmark with 1,632 tasks across five separate domains and nineteen simulation skills. The tasks check whether models can predict the environment's response to a specific action given the full agent trajectory by understanding earlier state changes, following environment rules, and predicting the effects of actions on both related and unrelated objects. We compare the predicted environment response with an execution-derived reference, using a hybrid architecture with both deterministic gates and a semantic judge. Among 20 general-purpose LLMs and specialized text world models, GPT-6 Astra achieves the highest task success rate at 49.57%. We find that model accuracy decreases as actions affect a larger portion of the environment. Specifically, when the agent's changes must propagate to dependent objects, task success drops to an average of 5.1% across all 20 models. Although…

    Code
  • arXiv cs.AIOct 15

    Brain-Aligned Multimodal LLMs for Social and Emotional Understanding of Cartoon Movies

    Yiran Huang, Zeyong Zhang, Bharat Biswal, Xin Di, Mengjia Xu

    Multimodal large language models (MLLMs) offer scalable annotations of social and affective content, but their temporal agreement with human judgments and neural predictive value require further evaluation. We compared diffusion-based and autoregressive MLLMs with continuous human Theory of Mind (ToM) and affective valence ratings across three short cartoon movies. Behavioral analyses assessed temporally aligned Pearson correlations, rating distributions, and the effects of preceding scene descriptions. Ratings from each source were separately used in subject-specific regression models to predict regional fMRI responses. Model ratings captured aspects of human temporal variation despite systematic distributional differences, with generally stronger alignment for valence than ToM. Preceding context improved alignment in some conditions, depending on the model and movie. In \emph{The Present}, more regions showed significant encoding for MLLM ratings than for human ratings, whereas effects were more limited in the other movies. Spatial overlap across rating sources occurred mainly among MLLMs; overlap between human and model ratings was limited and involved primarily visual,…

    PDF
  • arXiv cs.DBOct 15

    Data Provenance Aggregation and Structural Descriptors for Query-Template Identification

    Paulo Pintor, Rogério Costa, José Moreira

    Runtime query similarity identification supports several activities, including workload analysis, identifying recurring behaviour, auditing, debugging, and anomaly detection. Existing methods for evaluating query similarity mostly rely on SQL text, execution plans, or result values but do not account for input data or how results are derived during query execution. This paper proposes a novel approach using data provenance for query-template identification. We construct query-level profiles that capture explicit data dependencies, occurrence frequencies, and structural properties by aggregating tuple-level Lineage and Why-provenance across entire query results. We also derive Provenance Structural Descriptors (PSD), which summarise these profiles using a small set of numerical features. We evaluate our proposals using these profiles to identify query templates over \(12{,}500\) distinct query instances generated from parametrised TPC-DS query templates. The experimental evaluation shows that query templates can be identified solely from their provenance footprints, and that accuracy improves as more historical data becomes available. It also shows that PSD achieve high…

    PDF
  • arXiv cs.IROct 15

    NoveltyScope: A Multi-Agent Research Assistant for Evidence-Grounded Novelty Assessment of Scientific Papers

    Yueran Tian, Huizhi Liang

    NoveltyScope is a prototype that compares a scientific paper with retrieved prior work and produces a structured report and a five-level novelty score. The system extracts the core task and at most two author-claimed contributions, then searches a closed local corpus using BM25 and dense retrieval with reciprocal rank fusion. Contribution comparisons request paired passages for potential refutations, and quotations are checked against cached source text. Four scoring roles (Prosecutor, Defender, Judge, and Critic) use the resulting evidence, with at most one revision of the Judge's score. Evaluation uses 50 class-balanced RINoBench samples whose idea-level labels are retained for full-paper input. Mean absolute error is 1.48 and 1.26 for single-LLM and multi-agent scoring with Gemini, respectively, and 1.22 and 1.16 with Qwen3. The vector-similarity baseline has an error of 1.68. A HiCLIP case study illustrates the contribution comparisons and paired evidence passages. Overall, the results demonstrate the feasibility of evidence-grounded novelty assessment and show that the multi-agent configurations achieve lower scoring errors than their single-LLM counterparts across both…

    PDF
  • arXiv cs.CVOct 15

    Thinking from Above: Efficient Spatial Reasoning with Bird's-Eye-View Visual Tokens

    Faizan Siddiqui, Nirav Savaliya, Sahith Reddy Chada, Enna Sachdeva

    Existing video multimodal large language models (MLLMs) organize observations primarily in time, but embodied spatial reasoning requires organizing them in space. Consequently, their visual representations can remain locally consistent across nearby frames while lacking a persistent spatial context that is stable across viewpoints and time. We exploit depth and camera pose, which are naturally available to embodied agents, to explicitly establish this spatial correspondence. We introduce Cambrian-BEV, which extends Cambrian-S with a parameter-free geometric tokenization scheme that back-projects visual patch features from each frame into a shared bird's-eye-view (BEV) coordinate frame and averages features that fall within the same spatial cell. Thus, observations of the same physical location, regardless of viewpoint or time step, are aggregated into a common spatial token. In addition to providing a persistent scene representation, this formulation acts as an efficient compression mechanism: 128 frames containing approximately 100K DINOv3 patch features are consolidated into a fixed 27$\times$27 grid of only 729 BEV tokens, cutting LLM prefill time by $2.9\times$ and peak…

    PDF
Load more
PDF
PDF
PDF