Searcharxiv⌕ Search

arXiv subjects

Yoichi Sato

Publications and source records attributed to Yoichi Sato.

At least 19 recordsLinked to original sources
arXiv2026

Computational Prosopography across a Millennium: Mathematically Oriented Lineages Traced from the Fields Medalists

We reconstruct the mentor--student network through which documented scholarly training passed across roughly nine centuries, and subject both the network and the means of reconstructing it to source criticism. From Wikidata, which aggregates the Mathematics Genealogy Project and the MacTutor Archive, we extract approximately 470,000 mentor--student assertions, yielding a directed acyclic graph of 372,853 persons. Using all 64 historical Fields Medalists as a fixed, ex ante tracer set, backward traversal enumerates some 25.5 million distinct paths reaching 57 generations. Three structural observations follow. Genealogical traffic through Leibniz forms an hourglass: thin upstream, 5.3 paths per node on average, and thick downstream, 53.4, a ratio near 10:1, with no counterpart at Newton, who lies on only four of the 64 lineages. Across a window centered on Leibniz, seven independently extracted predicate dimensions reorganize together, and recorded learned-society membership rises from 6.5 to 82.1 percent of the cohort. Upstream, 54 of the 64 lineages converge on the same five twelfth- and thirteenth-century Islamic and Byzantine scholars before terminating at an eleventh-century boundary we name the Monastery Wall. We argue that such observations cannot be assessed without tool criticism. The traversal engine is algebraically reversible, so every ranking decision it makes can be reconstructed afterward. We characterize its measurement bias in closed form, show that the macro-structures survive switching that bias off, and report the family of lineages the traversal returns at different resolutions rather than a single ranked list.

physics.soc-ph↗
arXiv2026

HelloWorld: Enabling Socially Interactive Characters in Video World Models

Despite the remarkable recent progress of video world models, social interaction between users and the characters within these worlds remains unsupported. To fill this gap, we present HelloWorld, a video world model that enables social interaction with in-world characters. With a single button press, users can prompt the on-screen character to respond toward the camera, e.g., turning to the viewer, waving, nodding, or speaking a short greeting. To make these interactions natural, we propose a self-distillation pipeline that finetunes the video generation model on data synthesized by itself. Each synthesized clip contains both social interactions and camera motion, allowing the model to learn camera-pose conditioning without degrading interaction quality. At inference, we further introduce a training-free module that determines when the interaction occurs. Upon a button press, it modulates the cross-attention masks of the DiT so that the interaction-related text prompt attends only to the frames within the press window, temporally localizing the character's response. We further build HelloWorldBench, a 400-sample benchmark with three social interaction metrics alongside three conventional metrics, for evaluation. Experiments demonstrate that HelloWorld surpasses a variety of baselines in interaction quality, while maintaining state-of-the-art picture aesthetics and camera-pose following. Project page: https://github.com/AlayaLab/HelloWorld

cs.CV↗
arXiv2026

SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation

Recent years have witnessed an explosive trend of scaling ego-centric human videos for robot manipulation, yet it remains unclear which data actually benefits dexterous manipulation. We present SiMDex, a similarity-based data mining framework that casts human data selection for VLA post-training in dexterous manipulation as a recommendation problem. For each robot demonstration, SiMDex employs a three-layer recall-ranking-re-ranking pipeline to extract task-relevant subsets from a pool of ~32M egocentric human samples, operating in a morphology-agnostic action space that requires no changes to VLA architecture or training. Against a strong baseline trained with an equal amount of randomly sampled human data, SiMDex uses only ~1.49M mined samples (<5% of the pool) yet improves the overall success rate from 47.7% to 61.1%, showing that selective curation outperforms indiscriminate data mixing.

cs.RO↗
arXiv2026

How to Build Marcus's Algebraic Mind: From Thagard's Brain--Mind Viewpoint

This paper reports a convergence neither program was looking for. Marcus's The Algebraic Mind named three things any architecture needs -- operations over variables, recursive structure, and individuals distinct from kinds -- showed multilayer perceptrons have none, and left a register-and-treelet implementation as conjecture. Thagard's Brain-Mind ran it from the other end, making binding the mechanism from which the whole of mind is assembled, and circular convolution load-bearing. Marcus leaves his register algebra open; Thagard's is lossy, degrading under the very recursion his own account demands. VaCoAl is a hyperdimensional computing architecture built end-to-end on XOR-and-shift over GF(2) via primitive-polynomial LFSRs; PyVaCoAl is its extended software realization (all results here); the silicon substrate exists as CASRAM. Bind(R,F) = R XOR Shift(F) is exactly reversible and non-commutative: it supplies all three pillars at fixed dimension and removes convolution's depth degradation. Capability: exact reversible binding at O(N) yields compositional generalization with post-hoc auditability, which no lossy or learned substrate offers. Necessity: two independent architecture programs and the dentate gyrus-CA3 circuit require the same algebra -- convergence, not biomimicry. New here: discrimination and failure-tolerance are one. Repair every collision (RR = 1) and the system is bit-identical to a hash dictionary: candidates become indistinguishable and the confidence path-integral collapses; a memory that never fails keeps no record of which routes were hard. Position: we do not surpass large language models but supply the auditable, multi-hop relational reasoning embeddings lack. No consciousness is implemented and no cognitive experiment reported; bit-exactness holds in silicon, approximately under biological noise; speed and power remain unbenchmarked.

cs.NE↗
arXiv2026

How to Build Marcus's Algebraic Mind: From Minsky's Emotion-Machine Viewpoint

This paper reports a step that had already been taken. Marcus's three components of an adequate cognitive architecture -- variables, recursive structure, individuals vs kinds -- left the neural substrate open; a companion paper answers it with VaCoAl, built on XOR-and-shift over GF(2). Those pillars are horizontal: how a mind represents the world. Minsky's Emotion Machine supplies the orthogonal, vertical dimension -- a mind reasoning about its own reasoning. The vertical step needed no new machinery. A representation exactly recoverable becomes introspection when what is recovered is the reasoner's own deliberative trace: Minsky's Reflective layer. Pillar 2 says nothing about whose structure is recovered; point the same unbind inward and Reflection follows. Only the argument changes. Capability: exact reversible binding at O(N), kept exact within a Frontier Size, yields a trace readable constituent by constituent: a self-report faithful by construction, not verbalization. Only exact-algebraic traces, not probabilistic ones, make the reflexive read faithful. Necessity: audit and valuation are one circuit at opposite settings of one parameter. Repair every collision and the trace is exactly auditable but no path outranks another; tolerate them and the CR2 decay that credits the direct route makes the read approximate. Position: we claim neither to have built the Reflective layer nor to surpass large language models; it supplies the auditable trace probabilistic deliberation cannot leave. The same substrate gives panalogy (content-addressable retrieval scored by CR) and credit assignment as counterfactual unbind-rebind, meeting Pearl's causal axis. Not claimed: Reflection's sufficient conditions (meta-control loop, context-tagging) are future work; Reflection is introspection, not evaluation; its reachability is argued, not shown; speed and power unbenchmarked.

cs.NE↗
arXiv2026

Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos

When should an intelligent assistant speak up without being asked? Continuous egocentric video offers rich, evolving context that enables a new form of assistance: one that is proactive rather than merely reactive. Yet existing approaches either wait passively for user queries or treat every detected event as requiring a response, without considering the user's history, current activity, or whether assistance would actually be welcome. We reframe proactive assistance as a context-dependent decision problem: the agent must not only perceive what is happening, but reason over accumulated temporal context to determine when and whether to intervene. To this end, we present Vinci2, a proactive egocentric assistance system that advances the on-device assistant Vinci from reactive response toward proactivity. On the evaluation side, we present EgoServe, the first large-scale benchmark for proactive assistance in continuous egocentric video. EgoServe comprises over 3,000 service instances organized along 4 temporal memory horizons, ranging from immediate safety alerts to long-term habit coaching, across 10 service categories. On the modeling side, we propose EgoMemo, a training-free, memory-augmented agent that maintains three complementary memory representations: multi-scale temporal summaries, a semantic knowledge graph, and visual embedding archives. At each timestep, EgoMemo performs retrieval-augmented reasoning to determine whether assistance is warranted and, if so, produces contextually grounded responses. Experiments demonstrate that EgoMemo establishes strong baselines on EgoServe while remaining competitive on existing egocentric benchmarks. Our benchmark and code are publicly available at \href{https://sitonggong.github.io/EgoServe-page/}{Vinci2}.

cs.CV↗
arXiv2026

Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?

Hand-object interaction (HOI) recognition requires capturing both hand manipulations and object transformations. However, existing video-language models often fall into shortcuts by relying on spurious correlations among hands, objects, or environmental context, rather than reasoning from the appearance and dynamics of hands and objects themselves. To address this limitation, we propose a new learning paradigm that combines (i) hand-object masked training, which enables robust reasoning from partial hand or object observations, and (ii) an HOI-dynamics-aware decoder that explicitly learns hand- and object-centric embeddings through auxiliary predictions of their locations and semantics, enhancing sensitivity to both cues. To systematically evaluate such cue-specific reasoning, we introduce Cue-Isolated HOI (CI-HOI), a new evaluation that assesses models' ability to predict actions from hand- and object-related cues independently. To enable CI-HOI, we curate the DEHOI testbed, which separates hand- and object-related observations for disentangled HOI evaluation through inpainting. Using DEHOI, we demonstrate both quantitatively and qualitatively that our training strategy exploits hand- and object-centric information more effectively than existing models. Our approach improves over existing models on DEHOI, standard action recognition, object state recognition, and even robot manipulation action recognition, leading to more robust HOI understanding.

cs.CV↗
arXiv2026

Institutions and the transmission of upper-tail human capital: scientific lineages across a millennium

What made useful knowledge cumulative was not discovery alone but the institutions that transmitted it. We provide the first exhaustive structural measurement of the network through which upper-tail human capital passed from master to student across a millennium. Using 470,000 mentor-student records from Wikidata (which integrates the Mathematics Genealogy Project and MacTutor Archive), and all 64 historical Fields Medalists as a fixed, ex ante tracer set, backward traversal yields a directed acyclic graph of 25.5 million paths reaching 57 generations. We document two institutional transitions. First, a 17th-century watershed concentrates lineage traffic on Leibniz: 47 of 64 lineages pass through him with a 10:1 downstream-to-upstream ratio, and seven independent attributes -- learned-society membership (a 46-fold rise per scholar), field, language, employer, institutional diversification, student production, and diffusion entropy -- re-organize coherently across the same window. This is the network signature of Mokyr's Republic of Letters, and it reframes the Newton-Leibniz priority dispute as a distinction between the possession and the transmission of upper-tail human capital: it is transmission that generates the spillovers on which growth depends. Second, 84% of lineages converge upstream on five 12th-13th-century Islamic and Byzantine scholars before terminating at an 11th-century boundary -- the ``Monastery Wall'' -- at which personal academic mentorship first becomes record-generating in Europe. Our claims are descriptive-structural, not causal. Because exhaustive traversal at this scale defeats standard tools, we also contribute a deterministic, algebraic graph-traversal instrument whose measurement bias we characterize in closed form, and report one emergent property of independent methodological interest.

cs.NE↗
arXiv2026

CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering

Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception to a deeper understanding of causal mechanisms. However, existing benchmarks rarely provide the fine-grained, grounded evidence needed to rigorously evaluate this capability. To address this gap, we introduce CaST-Bench, a benchmark for Causal Chain-Grounded Spatio-Temporal Video Reasoning. CaST-Bench presents complex causal questions that require models to identify and localize a chain of multiple spatio-temporal evidences. Through a human-AI collaborative pipeline, we construct a high-quality dataset of 2,066 questions over 1,015 videos, with causal chains annotated by temporal segments and bounding-box tracks. Furthermore, we design a comprehensive evaluation suite with novel metrics that assess not only answer correctness but also the capability for visual evidence grounded reasoning. This grounding is crucial for improving accuracy by mitigating spurious correlations and for enhancing user trust by making models more transparent. Our experiments show that current VLMs struggle with causal questions, largely due to their limited ability to construct precise and grounded causal chains. This highlights an important direction for improving future VLMs. Homepage: https://woven-by-toyota.github.io/CaST-Bench.

cs.CV↗
arXiv2026

Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?

Multimodal Large Language Models (MLLMs) are increasingly deployed in human-facing roles where personality perception is critical, yet existing benchmarks evaluate this capability solely on numerical Big Five score prediction, leaving open whether models truly perceive personality through behavioral understanding or merely prejudge through superficial pattern matching. We address this gap with three contributions. (i) A new task: we formalize Grounded Personality Reasoning (GPR), which requires MLLMs to anchor each Big Five rating in observable evidence through a chain of rating, reasoning, and grounding. (ii) A new dataset: we release MM-OCEAN (1,104 videos, 5,320 MCQs), produced by a multi-agent pipeline with human verification, with timestamped behavioral observations, evidence-grounded trait analyses, and seven categories of cue-grounding MCQs. (iii) Benchmark and analysis: we design a three-tier evaluation (rating, reasoning, grounding) plus four sample-level failure-mode metrics: Prejudice Rate (PR), Confabulation Rate (CR), Integration-failure Rate (IR), and Holistic-grounding Rate (HR), and benchmark 27 MLLMs (13 closed, 14 open). The analysis uncovers a striking Prejudice Gap: across the field, 51% of correct ratings are not grounded in retrieved cues, and the Holistic-Grounding Rate spans only 0-33.5%. These findings expose a disconnect between getting the right score and reasoning for the right reason, charting a roadmap for grounded social cognition in MLLMs.

cs.AI↗
arXiv2026

How to Build Marcus's Algebraic Mind: Algebro-Deterministic Substrate over Galois Fields

In The Algebraic Mind (2001), Marcus held that any adequate cognitive architecture needs operations over variables, recursively structured representations, and an individual/kind distinction, and that multilayer perceptrons support none of them; he left a register-and-treelet implementation as a conjecture. Twenty-five years later a memory architecture built for unrelated reasons (speed, power and cost on commodity silicon) meets that specification operation for operation, through one mechanism rather than three. PyVaCoAl/VaCoAl is a hyperdimensional computing architecture built end-to-end on one primitive: XOR-and-shift over GF(2), realised by primitive-polynomial linear-feedback shift registers (LFSRs). It gives reversible binding Bind(R,F) = R xor shift(F), non-commutative bundling that distinguishes "dog bites man" from "man bites dog", and address-space individual/kind separation, at fixed dimension. Capability: exact reversible binding at O(L) cost supplies each pillar as an architectural primitive, not a product of training, with inspectability no lossy substrate offers. Necessity: weaken the primitive to an approximate inverse, as circular convolution does, and all three pillars degrade together -- what cannot be exactly decomposed was never composed, only mixed. Position: this is not the mind, the brain is not an LFSR, and we do not beat large language models; the substrate supplies the auditable symbolic layer they structurally lack. We develop the correspondence pillar by pillar, recast the treelet as a register set identified by a primitive generator polynomial, cite a companion Perspective on the dentate gyrus-CA3 circuit as a biological instance, and show that inflecting an unseen pseudoverb is a rung-3 query in Pearl's sense. Bit-exact reversibility holds in silicon and only approximately under biological noise; biological claims are structural only.

cs.NE↗
arXiv2026

Bridging Silicon and the Hippocampus: Algebro-Deterministic Memory "VaCoAl" as a Substrate for Vector-HaSH and TEM

Vector-HaSH and the Tolman-Eichenbaum Machine (TEM) propose the hippocampal-entorhinal circuit factorizes memory via a grid-cell scaffold for compositional replay. Concurrently, human iEEG shows sharp-wave ripples gate recall and multi-hop replay fidelity decays multiplicatively. Yet, these fields lack a shared algebraic foundation. We introduce VaCoAl, an algebro-deterministic hyperdimensional memory architecture built on Galois-field linear-feedback shift registers. Its deterministic Galois-field diffusion offers a substrate-level alternative to Vector-HaSH's random projections, matching quasi-orthogonality while ensuring bit-exact reproducibility. Furthermore, the path-integral Confidence Ratio CR2 provides an algebraically tractable model for the empirically observed multiplicative replay decay. Biologically, VaCoAl's two operating regimes align with the EC-CA3 direct and EC-DG-CA3 trisynaptic pathways, explaining their 520-Myr conservation. Independent cellular evidence supports that the DG-CA3 pathway implements a biophysical homologue of Galois-field arithmetic. We also link this framework to Judea Pearl's Ladder of Causation. Reversible GF(2) binding provides the surgical algebra for the do-operator (Rung 2), and VaCoAl's dual-orthogonalizer architecture supplies the parallel substrate required for counterfactual reasoning (Rung 3). Ultimately, we prove these formal correspondences and derive testable iEEG predictions, uniting computational neuroscience, electrophysiology, and hyperdimensional computing.

cs.NE↗
arXiv2026

SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation

Video generation has advanced rapidly, producing photorealistic videos from text or image prompts. Meanwhile, film production and social robotics increasingly demand multi-person videos with rich social interactions, including conversations, gestures, and coordinated actions. However, existing models offer no explicit control over interactions, such as who performs which action, when it occurs, and toward whom it is directed. This often results in wrong person performing unintended actions (actor-action mismatch), disordered social dynamics, and wrong action targets. To address these challenges, we present SocialDirector, a training-free interaction controller that enhances the generation model by modulating cross-attention maps. SocialDirector contains two modules: Social Actor Masking and Directional Reweighting. Social Actor Masking constrains each person's visual tokens to attend only to their own textual descriptions via a spatiotemporal mask, avoiding actor-action mismatch and disordered social dynamics. Directional Reweighting amplifies attention to directional words (e.g., "leftward", "right"), leading each action towards its intended target. To evaluate generated social interactions, we annotate existing datasets with interaction descriptions and build a fully automated evaluation pipeline powered by open-source VLMs. Experiments on different video generation models show that SocialDirector significantly improves interaction fidelity and approaches the upper bound set by real videos.

cs.CV↗
arXiv2026

Beyond LLMs, Sparse Distributed Memory, and Neuromorphics

VaCoAl (Python: PyVaCoAl) attacks the Binding Problem algebraically rather than statistically: an SRAM/DRAM-CAM organised end-to-end around one primitive, XOR-and-shift over GF(2) via primitive-polynomial LFSRs. Rooted in Kanerva's Sparse Distributed Memory, it retrieves in a million-dimensional binary space by Galois-field diffusion; Binding and Unbinding are exactly reversible at O(L), giving compositional generalisation with post-hoc auditability. Unexpectedly, a path-dependent semantic selection mechanism emerges undesigned, functionally equivalent to Spike-Timing-Dependent Plasticity (STDP) and predictable a priori from a closed form matching measurement on tens of millions of records. It is the Don't Care (collision-tolerance) rule: not a defect to engineer away, but the source of its ability to rank paths by quality. Capability: reversible binding plus tolerated collisions yields a path-integral confidence measure (CR2) ranking candidates by accumulated reliability, absent from hash-based search. Necessity: repair the collisions fully and the ranking vanishes; a memory that never fails has no record of which paths were difficult. Position: we do not surpass large language models; the substrate is orthogonal, supplying the auditable path-ranking layer they lack. A mentor-student ontology of ~470,000 WIKIDATA scholars, traversed backwards from all 64 Fields Medalists to depth 57 and >25.5M paths, stress-tests multi-hop reasoning over a large DAG. Ablation shows Don't Care imposing a depth-dependent exponential penalty that prunes circuitous routes and preserves direct ones: an Occam's razor. Per-generation CR1 stays within 0.995-0.999, yet cumulative CR2 decays monotonically to ~0.905 by generation 56, matching the closed form 0.997^56 = 0.846 within observed variation. All measurements are from PyVaCoAl, a software DRAM-CAM; speed and power figures are projections.

cs.NE↗
arXiv2026

Egocentric Gaze Estimation via Neck-Mounted Camera

This paper introduces neck-mounted view gaze estimation, a new task that estimates user gaze from the neck-mounted camera perspective. Prior work on egocentric gaze estimation, which predicts device wearer's gaze location within the camera's field of view, mainly focuses on head-mounted cameras while alternative viewpoints remain underexplored. To bridge this gap, we collect the first dataset for this task, consisting of approximately 4 hours of video collected from 8 participants during everyday activities. We evaluate a transformer-based gaze estimation model, GLC, on the new dataset and propose two extensions: an auxiliary gaze out-of-bound classification task and a multi-view co-learning approach that jointly trains head-view and neck-view models using a geometry-aware auxiliary loss. Experimental results show that incorporating gaze out-of-bound classification improves performance over standard fine-tuning, while the co-learning approach does not yield gains. We further analyze these results and discuss implications for neck-mounted gaze estimation.

cs.CV↗
arXiv2025

The N-Body Problem: Parallel Execution from Single-Person Egocentric Video

Humans can intuitively parallelise complex activities, but can a model predict this from observing a single person? Given one egocentric video, we introduce the N-Body Problem: predicting how N individuals, can hypothetically perform the same set of tasks. The goal is to maximise speed-up, but naive assignment of video segments to individuals often violates real-world constraints, leading to physically impossible scenarios like two people using the same object or occupying the same space. To quantify this, we formalise the N-Body Problem and propose a suite of metrics to evaluate both performance (speed-up, task coverage) and feasibility (spatial collisions, object conflicts and causal constraints). As a proof of concept, we introduce a structured prompting strategy that guides a Vision-Language Model (VLM) to reason about the 3D environment, object usage, and temporal dependencies, producing a viable parallel execution. On 100 videos from EPIC-Kitchens and HD-EPIC, for $N = 2$, our structured prompt improves action coverage by 45% over a baseline prompt for Gemini 2.5 Pro, while simultaneously slashing collision rates, object and causal conflicts by 51%, 52% and 55% respectively.

cs.CV↗
arXiv2025

HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics

Hand-object interaction (HOI) inherently involves dynamics where human manipulations produce distinct spatio-temporal effects on objects. However, existing semantic HOI benchmarks focused either on manipulation or on the resulting effects at a coarse level, lacking fine-grained spatio-temporal reasoning to capture the underlying dynamics in HOI. We introduce HanDyVQA, a fine-grained video question-answering benchmark that comprehensively covers both the manipulation and effect aspects of HOI. HanDyVQA comprises six complementary question types (Action, Process, Objects, Location, State Change, and Object Parts), totalling 11.1K multiple-choice QA pairs. Collected QA pairs recognizing manipulation styles, hand/object motions, and part-level state changes. HanDyVQA also includes 10.3K segmentation masks for Objects and Object Parts questions, enabling the evaluation of object/part-level reasoning in video object segmentation. We evaluated recent video foundation models on our benchmark and found that even the best-performing model, Gemini-2.5-Pro, reached only 73% average accuracy, which is far from human performance (97%). Further analysis shows the remaining challenges in spatial relationship, motion, and part-level geometric understanding. We also found that integrating explicit HOI-related cues into visual features improves performance, offering insights for developing future models with a deeper understanding of HOI dynamics.

cs.CV↗
arXiv2025

Multi-speaker Attention Alignment for Multimodal Social Interaction

Understanding social interaction in video requires reasoning over a dynamic interplay of verbal and non-verbal cues: who is speaking, to whom, and with what gaze or gestures. While Multimodal Large Language Models (MLLMs) are natural candidates, simply adding visual inputs yields surprisingly inconsistent gains on social tasks. Our quantitative analysis of cross-modal attention inside state-of-the-art MLLMs reveals a core failure mode: in multi-speaker scenes, visual and textual tokens lack speaker-consistent alignment, exhibiting substantially weaker cross-modal attention than in object-centric images. To address this, we propose a multimodal multi-speaker attention alignment method that can be integrated into existing MLLMs. First, we introduce dynamic cross-modal head selection to identify attention heads most responsible for grounding. Then, an adaptive social-aware attention bias, computed from existing attention patterns and speaker locations, is injected into the attention mechanism. This bias reinforces alignment between a speaker's visual representation and their utterances without introducing trainable parameters or architectural changes. We integrate our method into three distinct MLLMs (LLaVA-NeXT-Video, Qwen2.5-VL, and InternVL3) and evaluate on three benchmarks (TVQA+, MMSI, OnlineMMSI). Across four social tasks, results demonstrate that our approach improves the ability of MLLMs and achieves state-of-the-art results. Attention visualizations confirm our method successfully focuses the model on speaker-relevant regions, enabling more robust multi-party social reasoning. Our implementation and model will be available at https://github.com/ut-vision/SocialInteraction.

cs.CV↗