arXiv subjects

Sungwoo Kim

Publications and source records attributed to Sungwoo Kim.

4 recordsLinked to original sources

arXiv2026

PUBG Ally: A Conversational Embodied Agent as an AI Teammate

We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building such a teammate requires combining two difficult capabilities: it must perceive and respond to a constantly changing game world under strict latency constraints while interacting naturally with players, keeping its speech synchronized with its actions. Ally therefore combines agentic tool use with real-time game control. A language-model agent uses a controlled interface to inspect game information, interpret player speech, maintain context, decide what to say, and issue high-level action choices that steer a faster control layer for movement, combat, and recovery. Because the player's and Ally's speech and actions continually shape each other and the course of the match, training requires data from actual gameplay. We therefore collect data across nearly 39k sessions in which real players play alongside Ally, recording gameplay, player speech, agent decisions, tool use, actions, and player feedback, and use these records for iterative training. To evaluate teammate quality, we use player feedback and preference comparisons to identify gaps between offline evaluations and player preferences, and iteratively refine the evaluation criteria. Deploying Ally in live service further requires low-latency on-device execution and safeguards for player-facing communication, which we address through model compression, context compaction, targeted safety training, runtime guardrails, and memory redaction. During the live service, we surveyed players in 141 countries. Among respondents whose play with Ally was confirmed in game records, positive responses exceeded negative responses by 25.1 percentage points when asked whether they would recommend Ally, with players describing Ally not only as a tool but also as a teammate or companion.

cs.AI↗

arXiv2026

SoK: Kicking CAN Down the Road. Systematizing CAN Security Knowledge

For decades, the Controller Area Network (CAN) has served as the primary in-vehicle bus (IVB), extending its use to many non-vehicular systems. In recent years, CAN security has been intensively scrutinized, yielding extensive research literature. Despite its wealth, the literature lacks structured systematization, complicating efforts to assess and compare attack severity, defense efficacy, security gaps, and root causes. This leaves many defenders uncertain about the relevance of specific attacks or defenses to their systems, and even whether CAN's security problems are truly CAN-specific. As newer IVBs emerge, this matters beyond CAN: if CAN's root causes are not CAN-specific, replacing CAN may only move its problems to a new standard. In this paper, we systematize CAN security knowledge, presenting a comprehensive taxonomy and assessment models of attackers, attacks, and defenses. We identify replicable attacks and defense gaps, and investigate their root causes to determine their exclusivity to the CAN standard. We then investigate whether those root causes appear in three emerging IVBs and assess their effectiveness in solving fundamental CAN security problems. Our findings challenge common perceptions: CAN is more securable than perceived, most of its insecurity root causes are shared across IVBs, and merely adopting newer IVB technology does not solve persistent security problems. We conclude by suggesting that securing future in-vehicle communication requires addressing shared root causes, and we propose four research directions with the most promising potential.

cs.CR↗

arXiv2025

MARché: Fast Masked Autoregressive Image Generation with Cache-Aware Attention

Masked autoregressive (MAR) models unify the strengths of masked and autoregressive generation by predicting tokens in a fixed order using bidirectional attention for image generation. While effective, MAR models suffer from significant computational overhead, as they recompute attention and feed-forward representations for all tokens at every decoding step, despite most tokens remaining semantically stable across steps. We propose a training-free generation framework MARché to address this inefficiency through two key components: cache-aware attention and selective KV refresh. Cache-aware attention partitions tokens into active and cached sets, enabling separate computation paths that allow efficient reuse of previously computed key/value projections without compromising full-context modeling. But a cached token cannot be used indefinitely without recomputation due to the changing contextual information over multiple steps. MARché recognizes this challenge and applies a technique called selective KV refresh. Selective KV refresh identifies contextually relevant tokens based on attention scores from newly generated tokens and updates only those tokens that require recomputation, while preserving image generation quality. MARché significantly reduces redundant computation in MAR without modifying the underlying architecture. Empirically, MARché achieves up to 1.7x speedup with negligible impact on image quality, offering a scalable and broadly applicable solution for efficient masked transformer generation.

cs.LG↗

arXiv2025

Posted Price versus Hybrid Mechanisms in Freight Transportation Marketplaces

We consider a freight platform that serves as an intermediary between shippers and carriers in a truckload transportation network. The platform's objective is to design a policy that determines prices for shippers and payments to carriers, as well as how carriers are matched to loads to be transported, to maximize its long-run average profit. We propose a two-stage decision framework to model carriers' load choice behavior, where carriers choose a lane according to the multinomial logit (MNL) model based on the platform's posted price in the first stage and book a load in the second stage. We analyze two types of carrier-side mechanisms commonly used by freight platforms: a posted price mechanism and a hybrid mechanism where carriers can either book loads at posted price or submit their bids in an auction. The proposed mechanisms are constructed using a fluid approximation model to incorporate carrier interactions in the freight network. We show that the hybrid mechanism has higher profits than the posted price mechanism. We prove tight bounds between these mechanisms for varying market sizes. The findings are validated through a numerical simulation using industry data from the U.S. freight market.

math.OC↗