Artificial Intelligence
Asymmetric Collapse in Model Merging: When Refusal Over- writes Recognition
Aarnav Choudhary, Matheus Fonseca Rocha, Jiwon Seo et al. (+2 more)
Model merging is often used to combine capabilities from separately fine-tuned models without additional training, but it is unclear whether standard merging methods preserve multiple safety-relevant behaviors simultaneously. We study this question through a controlled case study using two Gemma-3-1B-IT finetunes on two complementary safety objectives: CARES harm-level classification and WildJailbreak
adversarial refusal. We merge the two fine-tunes using Linear, SLERP, TIES, and DARE-TIES, and evaluate the merged models on classification accuracy, attack resistance, and benign compliance. Across all four methods, attack resistance transfers significantly more than classification accuracy: merged models retain 81-85% jailbreak refusal rates while CARES accuracy falls to at most 12.9%. Weight-space measurements suggest that this asymmetry is not caused by strongly opposing task-vector directions: the two task vectors are nearly orthogonal (cosine similarity 0.011). Instead, the refusal fine-tune induces consistently larger per-layer task-vector magnitudes, causing magnitude-sensitive methods to favor refusal updates. These results show that standard model merging can collapse safety recognition into broad refusal when safety-relevant task vectors differ substantially in scale.
Read the full abstract ▾
All authors Aarnav Choudhary, Matheus Fonseca Rocha, Jiwon Seo, Vasu Sharma, Maheep Chaudhary
Artificial Intelligence · Cross-listed from cs.IR
Tokens are All You Need: Dual-purpose Semantic IDs for Achieving LLM-Level I/O Efficiency in recommendation systems
Baolei Li, Yiping Yuan, Yilin Zheng et al. (+6 more)
Large-scale recommendation systems face "
Memory Wall" bottlenecks due to massive, dense
embedding tables. While generative
retrieval uses discrete
tokens for IDs, high-dimensional context still relies on inefficient dense formats. Inspired by computer
vision data compression, we propose Dual-purpose Semantic IDs to achieve LLM-level I/O efficiency. Our methodology uses hierarchical quantization to condense continuous
embeddings into discrete Semantic IDs performing two concurrent roles: (1) Collaborative Identity: modeling user-item interactions via learnable
embedding table; and (2) Content Reconstruction: using a lightweight Semantic Decoder for on-the-fly
embedding approximation. This approach replaces massive vector storage with on-demand reconstruction, reducing system overhead and data footprints. We demonstrate the efficacy of our framework through offline evaluations and successful online deployment in production-scale ranking and
retrieval systems at a major
video sharing platform, showing that discrete
tokens are indeed all you need for highly efficient, content-rich recommendation.
Read the full abstract ▾
All authors Baolei Li, Yiping Yuan, Yilin Zheng, Likang Yin, Ling Liu, Fabio Soldo, Romer Rosales, Xinyang Yi, Lichan Hong
Artificial Intelligence · Cross-listed from cs.IR
HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Document
Xin He, Yili Wang, Wenqi Fan et al. (+4 more)
Question answering (QA) over complex documents requires models to retrieve and integrate evidence distributed across distant document regions and modalities.
Multimodal GraphRAG provides a promising direction by organizing document evidence with graph structures. However, existing methods often suffer from unreliable cross-modal evidence indexing and expensive graph traversal. To address these issues, we propose HVM-GraphRAG, a holistic-view
multimodal GraphRAG framework on complex document. HVM-GraphRAG uses a holistic view to guide graph construction, thereby reducing noisy and conflicting graph updates and building reliable indices between concept-level graph nodes and supporting
multimodal chunks. During
retrieval, HVM-GraphRAG searches over a compact concept-level graph and directly accesses supporting evidence through the constructed index, avoiding costly traversal over dense entity-level graphs. After obtaining the retrieved evidence, HVM-GraphRAG further reorganizes chunks into modality-specific groups, enabling the answering model to better integrate heterogeneous evidence. Experiments on three
datasets show that HVM-GraphRAG achieves the best answer performance in most evaluated settings while substantially improving online
retrieval efficiency over representative graph-based baselines.
Read the full abstract ▾
All authors Xin He, Yili Wang, Wenqi Fan, Qing Li, Qinggang Zhang, Yi Chang, Xin Wang
Artificial Intelligence · Cross-listed from cs.CV
DisasterTD: Disaster Toponym Disambiguation Using Multimodal LLMs and Cross-View Geolocalization
Wenping Yin, Ziqi Liu, Naixia Mou et al. (+3 more)
Social media imagery (SMI) provides timely and fine-grained ground perspectives that are valuable for situational awareness and emergency response. Unlike satellite or aerial imagery, SMI can capture disaster impacts and ground-level conditions in a timely manner. However, geographic references in SMI are often vague or ambiguous, making accurate geolocalization challenging. To address this issue, we propose DisasterTD, a disaster toponym disambiguation framework that integrates
multimodal large
language model (MLLMs)-based semantic
reasoning with cross-view geolocalization. First, MLLMs extract toponyms and generate candidate geolocations from noisy textual inputs. Then, cross-view matching between SMI, remote sensing imagery (RSI), and optionally street-view imagery (SVI) is used to verify and refine these candidate results. We evaluate DisasterTD on the Hurricane Harvey
dataset, where SMI is augmented with collected RSI and SVI to construct a cross-view
benchmark for disaster geolocalization. The
dataset is divided into four categories based on toponym clarity and ambiguity, allowing a fine-grained performance analysis across scenarios. Results show that DisasterTD consistently outperforms MLLM-only and cross-view-only baselines without disambiguation, achieving geolocalization accuracies of 71.62% within 1000 m, 62.36% within 500 m, 57.99% within 250 m, 52.09% within 100 m, and 47.01% within 50 m, while reducing the mean and median errors to 11.33 km and 0.68 km, respectively. The largest improvements appear in ambiguous toponyms, where semantic
reasoning with cross-view evidence reduces candidate dispersion and errors. These findings demonstrate the effectiveness of integrating MLLM-based candidate generation with cross-view verification for fine-grained disaster geolocalization.
Read the full abstract ▾
All authors Wenping Yin, Ziqi Liu, Naixia Mou, Weijia Li, Danfeng Hong, Hao Li
Artificial Intelligence
Cost-Aware Recovery-Pathway Identification and Bayesian Optimization for Autonomous Materials Discovery
Debajyoti Ray and Niranjan Srinivas
Autonomous laboratories automate experimental execution, but a campaign must also decide which recovery pathway merits optimization. We formulate this as a sequential decision problem with a discrete pathway-identification stage and a continuous within-pathway optimization stage under heterogeneous experimental costs. Our implementation, Coactive learning, combines a cost-sensitive
Bayesian hypothesis-discrimination policy motivated by EC2 (Golovin et al., 2010) with Gaussian-process
Bayesian optimization (Srinivas et al., 2010). Under explicitly stated assumptions, the expected spend of one fixed-budget campaign attempt is bounded by the expected pathway-identification cost plus the capped within-pathway optimization budget. We evaluate the method on synthetic
benchmarks constrained by selected results reported for PNNL's CICERO selective-precipitation study (Ritchhart et al., 2026). The method performs comparably to an oracle-pathway
Bayesian-optimization reference and to a strong split-plate baseline that discriminates pathways with its first plate, without receiving an oracle label for the correct pathway. It is given a candidate hypothesis space and a diagnostic likelihood model. On an NdFeB-inspired instance, it avoids the simulated penalty of a commit-first baseline that initially selects a plausible but inferior hydroxide pathway. This hypothetical wrong-first-commitment scenario is motivated by the hydroxide-oxalate performance contrast reported by CICERO. We characterize the sensitivity of these conclusions to the assumed cost model. The code and
benchmark are open source.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.HC
Visible to the Court: How AI Is (and Isn't) Litigated in U.S. Federal Court Opinions
Julie Yu, Rock Yuren Pang, Jevan Hutson et al. (+1 more)
In the United States, artificial intelligence (AI) is rapidly deployed amid limited federal regulation. With courts become a recurring forum in which AI-related practices are scrutinized, it is important to empirically understand the AI litigation landscape to date. We address this gap through a systematic review of 559 U.S. federal court opinions in which AI plays a role in the parties' contentions, taxonomizing (1) common topics of dispute, (2) the AI technologies implicated, and (3) the parties involved, including common plaintiff and defendant types. We identify seven recurring dispute areas, six categories of AI technologies at the center of litigation, and four types of common litigants, alongside legal doctrines used by the litigants. A comparison of this taxonomy to the AI Incident Database revealed substantial gaps in coverage, definitions, and prevalence between documented and litigated harms, suggesting courts capture only part of the AI risk landscape. In addition, we found that court decisions primarily rely on pre-existing legal doctrines to manage AI rather than making new AI-specific laws, producing a form of "piecemeal" AI governance. As a result, federal court outcomes are shaped less by where AI has caused harms and more by which harms are cognizable under existing statutes, leading to certain AI harms remaining unresolved.
Read the full abstract ▾
All authors Julie Yu, Rock Yuren Pang, Jevan Hutson, Katharina Reinecke
Artificial Intelligence · Cross-listed from cond-mat.mtrl-sci
Harnessing X-ray Absorption Spectroscopy Data through Multimodal Mining of Battery Literature
Tanjin He, Aikaterini Vriza, Logan Ward et al. (+7 more)
X-ray absorption spectroscopy (XAS) is central to understanding the local electronic and atomic structure of materials, yet most published spectra remain inaccessible to data-driven analysis because they are embedded in figures and described through fragmented textual context in the literature. Here, we use
multimodal (image and text) literature mining to transform this dispersed knowledge into an AI-ready experimental data resource. We developed a scalable spectroscopy data digitization pipeline that identifies XAS figures in full-text articles, digitizes spectral curves, and links each spectrum to accompanying metadata on the measured edge and material. Applying this pipeline to the battery literature produced an open
dataset of 13,740 XAS spectra, spanning 66 absorbing elements and diverse battery chemistries, with expert validation confirming accurate extraction of spectral and metadata information. By converting literature-embedded spectra into structured numerical data, this
dataset provides a foundation for large-scale XAS analysis, cross-laboratory comparison, high-throughput characterization, and autonomous discovery of advanced materials.
Read the full abstract ▾
All authors Tanjin He, Aikaterini Vriza, Logan Ward, Xu Huang, Yiming Chen, Anubhav Jain, Gerbrand Ceder, Rajeev S. Assary, Ian T. Foster, Maria K. Y. Chan
Artificial Intelligence · Cross-listed from cs.LG
Physics-Informed Neural Networks for Predicting Nitrous Oxide Flux
Freddy Yu, Jashanjeet Kaur Dhaliwal and Subhadeep Chakraborty
Nitrous
oxide (N$_2$O) is the dominant ozone-depleting substance emitted in the 21st century, and the third largest contributor to anthropogenic greenhouse gases due to its high potency and long atmospheric lifetime, with more than 70% of N$_2$O emissions occurring as a result of agricultural processes. Current approaches to predicting N$_2$O flux emissions include process-based models such as DayCent and Cycles, as well as classical AI models, but the application of Physics-Informed Neural Networks (PINNs) to predicting N$_2$O flux emissions is largely underexplored. Our paper draws upon the mechanistic equations that underlie the DayCent family of process-based models to construct a rigorously derived, literature-traceable physics residual. We then build and train an MLP-based PINN on a multi-site agricultural
dataset spanning four geographically distinct US agricultural sites. Across all tested values of the physics loss weighting hyperparameter $\lambda$, our PINN consistently and substantially outperformed uncalibrated Cycles simulation (R$^2=0.01$), with our MLP baseline achieving mean R$^2=0.411$ across ten random seeds. Physics constraints consistently degrade model performance in holdout validation, with marginal degradation at low $\lambda$ and significant degradation at high $\lambda$, but consistently improve model performance and reduce performance variability in leave-one-site-out validation. This suggests that physics constraints sacrifice in-distribution accuracy for out-of-distribution robustness, anchoring the model toward biogeochemically plausible behavior on unfamiliar soil conditions — though cross-site generalization remains challenging, with negative R$^2$ across all seeds and $\lambda$ values on our geographically distinct held-out site.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.MA
MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents
Belal S. Alsinglawi, Weizheng Wang, Junyi Wu et al. (+3 more)
In IoT-enabled smart-city settings, Uncrewed Aerial Vehicles (
UAVs) are evolving from passive sensing platforms into cyber-physical decision makers that must respect operational rules under degraded observations and ambiguous
language. Existing
UAV and
multimodal benchmarks cover aerial perception,
navigation, collaboration, and task
reasoning, but rarely test whether physical evidence, protocol constraints, and action risk stay coupled at critical decisions. We introduce MulRobBench, an offline, protocol-conditioned
benchmark for
Vision-
Language-Action (VLA)
UAV agents that links real
UAV multimodal observations, protocol-level security-policy constraints, and action-level cyber-physical safety within an auditable decision contract. The evaluation set contains 3,024 samples spanning 17 task-taxonomy nodes and 12 metric scoring dimensions, organized around context understanding,
multimodal evidence arbitration, degradation-aware
reasoning, and risk-aware action planning. MulRobBench reports controlled semantic scores alongside strict structural diagnostics for policy compliance, formatting, unsafe actions, parsing, and dimension-level validity. Across 17 uniformly audited models, the best semantic protocol-decision score reaches 0.5141 and the best strict mean scoring-dimension accuracy reaches 0.1599. A matched 20-anchor modality-removal study changes 4-15 action selections per model, showing both visual and textual inputs influence decisions while the strongest input condition varies across metrics. Per-dimension and conditional analyses identify modality-trust selection, constraint extraction, strong glare, missing data, and high-
entropy operator shorthand as principal sources of action instability. The central challenge is thus stable coupling of degraded evidence, security-policy constraints, and risk-bearing action, not isolated scene recognition.
Read the full abstract ▾
All authors Belal S. Alsinglawi, Weizheng Wang, Junyi Wu, Lianhai Lin, Merouane Debbah, Izzat Alsmadi
Artificial Intelligence · Cross-listed from cs.LG
A Coulomb Particle Model for Learning Kernel Attention in Transformers
Masoud Badiei Khuzani, Sharath Honnaiah, Atiq Islam et al. (+2 more)
Randomized features provide a scalable approximation to kernel machines, but their performance depends strongly on the choice of feature distribution. We propose a particle-based method that learns this distribution by optimizing kernel-target
alignment while regularizing particles with a Riesz/Coulomb repulsive potential. The resulting
Hamiltonian yields diverse, task-adaptive random features and admits a mean-field description through a McKean–Vlasov equation. We instantiate the method in linearized
Transformer attention by learning positive random-feature maps in a first
alignment phase, then freezing the kernel and training the remaining network parameters with cross-
entropy. Experiments on synthetic classification and sentence-level
benchmarks show that learned kernelized
attention can improve accuracy, calibration, and robustness for several feature maps while preserving linear-
attention inference complexity.
Read the full abstract ▾
All authors Masoud Badiei Khuzani, Sharath Honnaiah, Atiq Islam, Alex Cozzi, Abraham Bagherjeiran
Artificial Intelligence
Understanding Human-like Solutions in Combinatorial Optimization via Learning and Search
Haijiang Yan, Jian-Qiao Zhu, Liqiang Huang et al. (+1 more)
Humans often find good solutions to combinatorial optimization problems that are computationally hard even for advanced computer
algorithms. In the Euclidean traveling salesman problems (TSP), people rapidly produce tours that are near-optimal, despite severe limits on time and computation. What makes a tour human-like, and how might such solutions be learned? Here we address these questions through a large-scale behavioral and computational investigation of human performance in Euclidean TSP. We sampled a broad space of TSP instances, collected human solutions, and compared them with neural policies based on Pointer Networks, which are recurrent neural networks with an
attention-based pointing mechanism that define probability distributions over valid tours. We trained these networks under multiple objectives, including reinforcement learning (RL), supervised learning from optimal tours, supervised learning from human tours, and RL fine-tuning after optimal-supervised pretraining. Human tours were not identical to optimal tours, but occupied a near-optimal
geometric basin: they shared many structural properties with optimal solutions while preserving systematic human-specific deviations. The best account of human tours was not direct imitation of optimal tours, but a model pretrained on optimal tours, fine-tuned by RL, and decoded through $\text{Best-of-}N$ sampling. These findings suggest that human-like solutions may emerge from a combination of structured supervised learning, RL, and test-time search, echoing computational principles underlying many modern artificial intelligence systems.
Read the full abstract ▾
All authors Haijiang Yan, Jian-Qiao Zhu, Liqiang Huang, Ming Meng
Artificial Intelligence
Do Visual Features Improve Other-Initiated Repair Detection? A Dyadic Multimodal Approach
Anh Ngo, Nicolas Rollet, Catherine Pelachaud et al. (+1 more)
Other-initiated Self-repair, or in short Other-initiated Repair (OIR), is an essential mechanism in conversational interaction, whereby a recipient signals a problem in speaking, hearing, or understanding, prompting the previous speaker to resolve it. In the case of conversational
agents, it is essential to accurately identify these repair initiation strategies to address communication breakdowns efficiently. While conversational analysis studies have shown that OIR initiation is accompanied by both verbal and non-verbal signals such as gaze shifts, facial expressions, body postures, and hand gestures, existing computational approaches rely mainly on text and audio. This paper introduces a novel
multimodal model for OIR detection and classification, incorporating a set of visual features drawn from conversation analysis. We evaluate our approach on two corpora with distinct
languages and interaction settings. Results demonstrate that visual information consistently improves performance over text and audio baselines, and provide insights into cross-modal feature contributions across two corpora.
Read the full abstract ▾
All authors Anh Ngo, Nicolas Rollet, Catherine Pelachaud, Chloé Clavel
Artificial Intelligence · Cross-listed from cs.NE
Limbomorphs
Alex Alvarez and Michael Levin
Artificial life systems are typically defined by a set of dynamical rules over an environment, an
agent, or both, from which lifelike patterns may emerge. Gifbreeder is an animated version of the interactive evolutionary computation (IEC) platform Picbreeder, and was initially created to generate visual art. Instead of encoding the
agent or the environment, Gifbreeder genomes encode a spatiotemporal field and evolve through the user's aesthetic selection. The evolved expressions can sometimes resemble motile lifelike creatures that we term Limbomorphs, given that they exist in a deterministic three-second looping "limbo". We assess their behavior via input-space perturbations and find species-specific reactions to different kinds of perturbations. We discuss whether these reactions may reflect goal-directed behavior like
navigation, or merely the appearance of it, and more broadly how
agent-like dynamics may emerge in a system with no explicitly defined
agent, environment, or interaction rules.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
TriShieldRAG: 3 Rings, One Blind Spot in Layered Defenses for Retrieval-Augmented Generation
Susil Kumar Mohanty, Rohit Patel, Kosuru Yuvaraj et al. (+2 more)
Retrieval-Augmented Generation (RAG) grounds LLM answers in query-time retrieved documents, so reliability depends on what the retriever returns. PoisonedRAG (Zou et al., USENIX Security'25) showed five crafted documents mislead an undefended system in nearly 90% of cases, and that single-stage defenses give limited robustness. We propose TriShieldRAG, a three-layered framework: an Ingest Guard for document-level screening, a
Retrieval Scorer for trust-aware re-ranking, and a Cross-LLM Consensus over three diverse models. We reasoned that collectively screening, re-ranking and validating retrieved evidence would give complementary protection, limiting the ability of poisoned documents to succeed through any single failure. We evaluate against non-adaptive and adaptive poisoning. Non-adaptively, on the full 2.68M-passage Natural Questions (NQ) corpus with the original PoisonedRAG attack, it cuts attack success from 79 +/- 1.0% to 1 +/- 0.0%. Adaptive attacks expose fundamental limits of layering. By changing only the document formatting, without modifying the poison text or accessing the retriever, the attacker reduces the Ingest Guard score from 0.500 to 0.000 and bypasses it on all 500 tested documents across three corpora. The remaining layers then give no protection: 62 +/- 0.8% attack success against a 56 +/- 2.5% undefended baseline on NQ, and 85 +/- 0.6% against 86 +/- 0.6% on HotpotQA. Layered defenses relying on the same retrieved evidence fail together: poisoned context misleads both re-ranking and consensus validation. Minority-poison thresholds prove corpus-dependent, at 0.214, 0.251 and 0.558 rather than the derived 0.5; a closed form we proposed for these failed a pre-registered prediction and is retracted. Cross-model agreement is misleading, reaching 0.96 while attack success approaches 99%. We release the framework, the evasion-certification methodology and artifacts.
Read the full abstract ▾
All authors Susil Kumar Mohanty, Rohit Patel, Kosuru Yuvaraj, Jeenal Chaudhary, Disha Singhania
Artificial Intelligence · Cross-listed from cs.DB
Kalypso: Relational LLM Serving
Hojae Son, Md Ashraful Islam, Huy Gia Cao et al. (+2 more)
Large
language models are increasingly used as semantic operators for filtering, extracting, ranking, joining, and transforming unstructured data. Existing semantic query processing systems invoke request-centric LLM serving systems that are unaware of the query plan, leaving substantial performance opportunities unused. This paper introduces relational LLM serving, an abstraction that makes LLM serving aware of semantic query structure while preserving query semantics and output accuracy. The key opportunity is pipelined execution across semantic operators: when intermediate tuples flow directly from one operator to the next, their KV-cache state can be reused instead of recomputed. We present Kalypso, a relational LLM serving system that exposes an API for semantic query plans and executes them using an adaptive,
memory-aware scheduling
algorithm. Kalypso addresses a new online scheduling problem in which pipelined operator execution is coupled with GPU
memory pressure management to reuse KV-cache state in the serving engine before eviction. Its scheduler continuously adjusts
memory allocations to balance upstream parallelism, downstream progress, and GPU utilization. Our evaluation shows that Kalypso improves query completion time over baselines using request-centric LLM serving, with speedups up to 4.57x across diverse workloads, demonstrating that query-aware LLM serving can substantially improve the efficiency of semantic query execution.
Read the full abstract ▾
All authors Hojae Son, Md Ashraful Islam, Huy Gia Cao, Hui Guan, Marco Serafini
Artificial Intelligence · Cross-listed from cs.CL
Earnings25: A Comprehensive 500-Hour Speech Benchmark for Finance
Denglin Jiang, Haoran Zhou, Anshul Wadhawan et al. (+7 more)
We introduce Earnings25, a finance-domain
benchmark for evaluating automatic
speech recognition (ASR) on English-
language earnings calls under realistic conditions. Earnings25 comprises two complementary test sets: (i) testset-full, 498 hours of full English-
language S&P 500 earnings calls from Q4 2025, and (ii) testset-segmented, a 46-hour industry-balanced set of 290 segments sampled from English-
language U.S. earnings calls in 2025. The
benchmark provides aligned transcripts and structured metadata, including speaker roles, industry labels, and call structure, enabling speaker- and industry-aware evaluation beyond aggregate word error rate (WER). We report reproducible baselines for Whisper and Parakeet-TDT using standardized scoring.
Read the full abstract ▾
All authors Denglin Jiang, Haoran Zhou, Anshul Wadhawan, Brendan Fahy, Vinay Ramesh, David Weisberg, Dmitriy Derkachevskiy, Helen Sheehan, Srivas Prasad, Michele Franceschini
Artificial Intelligence
ACM: Agentic Context Management for Long Horizon Tasks
Xiaochuan Li, Ryan Ming, Meng Chu et al. (+3 more)
Agentic tasks are inherently long-horizon and multi-turn, constantly accumulating context through interactions with the environment. Existing context compression methods inevitably incur information loss and are triggered by rigid heuristic rules, leaving them misaligned with the
agent's evolving
reasoning focus. We propose Agentic Context Management (ACM), a framework that equips
agents with purpose-built context editing tools for lossless context management. Inspired by the interaction between short-term and long-term human
memory, the
agent autonomously decides when to compress its context, offloads discarded content to an external
memory system, and queries it on demand for later
retrieval. Building on this framework, we further develop a post-training pipeline that constructs high-quality demonstrations of context management and improves model performance on both agentic search and coding tasks. Further analysis reveals that effective context management reduces peak
token pressure, enables extended explorations, and yields more consistent solutions across independent trials. Code, data, and model checkpoints are available at https://github.com/lixiaochuan2020/agentic-context-management.
Read the full abstract ▾
All authors Xiaochuan Li, Ryan Ming, Meng Chu, Shuai Shao, Rong Jin, Chenyan Xiong
Artificial Intelligence · Cross-listed from cs.CL
Deovrat Mehendale, Aditya Mehndiratta, Dhruv Rathi et al. (+2 more)
In this work, we introduce Indic DiarBench, a speaker diarization and ASR
benchmark dataset spanning all 22 scheduled
languages of India. This corpus comprises approximately 108 hours of natural multi-speaker audio from near-field meetings, far-field recordings, and in-the-wild audios. All annotations are human-corrected with time-aligned speaker attributed transcriptions. The
dataset captures conversational nuance prevalent in Indian
speech, such as English code-mixing, dialectal variation, and frequent speaker overlap. To establish a baseline for joint ASR and diarization capabilities we evaluate leading systems including commercial
speech APIs and
multimodal large
language models. Indic DiarBench is released as an open-access resource to advance inclusive,
multilingual speech technology research for Indian
languages.
Read the full abstract ▾
All authors Deovrat Mehendale, Aditya Mehndiratta, Dhruv Rathi, Kaushal Bhogale, Mitesh M. Khapra
Artificial Intelligence · Cross-listed from cs.CL
A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever
Sietse Schelpe
Improving a
language model today means retraining it: enormous compute, a new opaque model each cycle, non-deterministic output. We take the opposite path: the model stays frozen, and a persistent
memory of verified solutions grows beside it. Once a problem family is solved and has passed an independent verification step that never consults the answer key, every new instance of that family is answered at zero generation
tokens, bit-exact, deterministically. Across 180 fresh instances spanning nine problem families, four architectures from four vendors - dense and mixture-of-experts - each score 180/180 at zero generation
tokens per answer: execution-bound capability decoupled from parameter scaling. A negative control attributes the capability fully to the
memory: emptied, it solves nothing. The same verify-before-store contract holds for open-ended
reasoning: 88/88 consistency-gated acceptances across all four models, machine-checked formal proof, and
reasoning-method transfer at 77/80.
Memory selection takes 1.4 microseconds; a full reuse completes in 6-23 ms at 36 mWh. Approximate similarity
retrieval selects the wrong item 94.3% of the time on a 4,500-item verified store where exact addressing makes zero errors. The store also serves as working context at a scale no shipped engine matches: a 6,000,000-
token movable window on a single 46 GB GPU at flat
memory, where vLLM stops at 30,399
tokens and SGLang silently truncates past 32,000. On published
benchmarks, frontier models remain far ahead of any 12B at raw from-scratch
reasoning; on everything this system has solved and verified, the comparison inverts: a frontier API call pays a fresh generation pass on every query, forever, while verified reuse costs zero
tokens and returns the identical bits every time. A public testbench with free, rate-limited access accompanies this report: https://corbenic-galahad-bench.hf.space
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
How Context Attribution Handles What the Model Already Knows
Quoc-Huy Trinh, Lin Zhu and Sebastian Szyller
Context attribution methods for large
language models (LLMs) identify which input context contributes to the model response. Recent works show the initial success in attributing the con- tributive score of the contexts. However, we observe that when the context overlaps with the training data, these methods can- not disentangle in-context from in-weight (IW) contributions, producing unreliable scores. Based on this observation, in this work, we introduce: 1) an evaluation protocol that relies on four new metrics (base-model context attribution score (BCS), cross-model context attribution consistency (CAC), attribution preservation score (APS), source separation pre- cision (SSP)) and 2) a
benchmark dataset (WMDP-Cyber++) with ground-truth provenance labels to systematically assess attribution under IW overlap. In our experiments across four well-known context attribution methods, we demonstrate that they provide unfaithful attribution when the knowledge from the context also exists in the weights. Finally, we adapt these methods for source separation (IW vs. in-context learning (ICL)) and show that they cannot do the disentanglement based on the contributive score
Read the full abstract ▾
Artificial Intelligence
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
Qinsi Wang, Jing Shi, Huazheng Wang et al. (+8 more)
Reinforcement Learning with Verifiable Rewards (RLVR) has driven recent progress in
reasoning-oriented large
language models (LLMs) by enabling large-scale optimization. However, its applicability remains largely limited to domains such as mathematics and coding, where correctness can be deterministically verifiable. Open-ended tasks instead often rely on human preferences, reward models, or LLM-based judges, introducing evaluation bias, judge capability bottlenecks, and additional inference costs. Drawing on the principle of self-supervised learning, which constructs pretext tasks to derive supervision from the data itself, we propose Reinforcement Learning with Self-Verifiable Rewards (RLSVR), a task-transformation-based training paradigm for extending RLVR to open-ended tasks. RLSVR transforms open-ended tasks into verifiable proxy environments whose internal rules and interaction outcomes automatically generate reward signals. We instantiate RLSVR with SpyRL, a Self-PlaY Reinforcement Learning method inspired by social deduction game Who Is the Spy?.
Agents receive asymmetric information, complete the same target task, and vote to identify a designated spy. Because the spy identity is predetermined, voting outcomes provide fully verifiable rewards, while successful identification remains closely related to output quality. Experiments on text summarization, creative writing, and mathematical
reasoning show that SpyRL outperforms existing self-improvement methods on non-verifiable tasks and yields consistent gains on verifiable
reasoning tasks. These results demonstrate that task transformation can extend scalable RLVR-based self-improvement beyond inherently verifiable domains. Models and code have been released at https://github.com/wangqinsi1/RLSVR/tree/SpyRL.
Read the full abstract ▾
All authors Qinsi Wang, Jing Shi, Huazheng Wang, Kun Wan, Yiran Wu, Bo Liu, Qingyun Wu, Hai Helen Li, Yiran Chen, Handong Zhao, Wentian Zhao
Artificial Intelligence · Cross-listed from cs.CV
PathScale-R1: Cross-scale Reasoning for Pathological Image Analysis
Chi Phan, Tianyi Zhang, Yufeng Wu et al. (+7 more)
Pathological diagnosis is inherently multi-scale, requiring the integration of global tissue architecture at low magnification with cellular morphology at higher magnification. However, existing pathology
benchmarks and
vision-
language models (VLMs) are still largely developed under single-scale settings, limiting their ability to learn clinically meaningful multi-magnification
reasoning. Moreover, naively constructed visual question answering (VQA) tasks may be susceptible to text-only or superficial visual shortcuts, leading to unreliable assessments of visual understanding. To address these limitations, we introduce a
benchmark and training framework for shortcut-resistant cross-scale pathology
reasoning. We design an
Adversarial Text-only Screening strategy for semantic
reasoning questions and a Structure-controlled Distractor Sampling strategy for visual grounding questions, encouraging models to rely on cross-scale visual evidence. Based on this pipeline, we construct PathScale-VQA, a high-quality cross-scale pathology VQA
benchmark with 10,373 multiple-choice questions grounded in 1,368 diagnostic paths across multiple magnification levels. Building on the semantic
reasoning set, PathScale-R1 is optimized through Difficulty-driven
Reasoning Distillation supervised fine-tuning followed by reinforcement learning with a Scale-aware
Reasoning Structure reward, which encourages the use of evidence across magnifications. Extensive experiments demonstrate state-of-the-art performance of PathScale-R1 on cross-scale
reasoning tasks and effective transfer to conventional single-scale pathology VQA. Our code is available at https://github.com/iMVR-PL/PathScale-R1.
Read the full abstract ▾
All authors Chi Phan, Tianyi Zhang, Yufeng Wu, Qiaochu Xue, Jiajie Zhang, Linghan Cai, Zeyu Liu, Sudong Wang, Yueming Jin, Dan Hu
Artificial Intelligence · Cross-listed from cs.CC
Maximum Satisfiability of Simple Temporal Problems
Johannes K. Fichte, Johanna Groven, Peter Jonsson et al. (+2 more)
The Simple Temporal Problem (STP) is a core framework for quantitative temporal constraints. As STP data can be inconsistent, we study MAXSTP: compute a maximum-cardinality consistent subset of constraints. This extension is NP-hard, and we analyze its parameterized complexity under measures that capture practically relevant instance features: the number of variables $n$ (instance scale), the maximum coefficient magnitude $k$ (numeric range), and structural parameters of the constraint graph such as treewidth $tw$ (decomposability) and vertex cover size $vc$ (density). We show that MAXSTP is W[1]-hard parameterized by $n$, implying that $n$ and parameters that depend on $n$ (including $tw$ and $vc$) are insufficient for fixed-parameter tractability. For combined parameters, we give an $O^*(k^n)$-time
algorithm, yielding single-exponential solvability for fixed $k$. While $k+tw$ remains W[1]-hard, MAXSTP is in XP via an $O^*((n\cdot k)^{tw})$
algorithm. Our results suggest that MAXSTP is often computationally harder than optimizing qualitative CSPs. We verify that many such problems (including RCC-8 and Allen's
algebra) are FPT when parameterized by $n$ or $tw$. However, we also demonstrate that FPT
algorithms for MAXSTP are indeed possible but with other parameters such as $k + vc$.
Read the full abstract ▾
All authors Johannes K. Fichte, Johanna Groven, Peter Jonsson, Victor Lagerkvist, Jorke M. de Vlas
Artificial Intelligence · Cross-listed from cs.RO
A Few Words Go a Long Way: Language Guided Robot Policy Synthesis
Daphne Chen, Archit Ritesh Jain, Eric Goossen et al. (+4 more)
While
vision-
language-action models have demonstrated impressive zero-shot manipulation capabilities, they remain fundamentally black box policies that are difficult to interpret, adapt, or correct when they inevitably fail. In this work, we propose ARCHITECT, a framework that treats
robot policy acquisition as an interactive program synthesis task. ARCHITECT leverages the
reasoning capabilities of LLM coding
agents to synthesize modular
robot programs that utilize a suite of perception and control tools. Unlike end-to-end models where distribution shift leads to unpredictable, cascading failures, our modular architecture allows users to isolate failures and localize feedback at the level of abstraction required. We introduce an iterative process where a human supervisor provides natural
language corrections to steer the policy. These corrections are grounded in the policy code by program execution traces and distilled into a persistent skill library, a form of long-term in-context learning which enables the
agent to accumulate a repertoire of reusable, interpretable behaviors. In a
benchmark evaluation on a Franka Panda
robot, ARCHITECT outperforms state-of-the-art VLA models and program synthesis baselines on complex, long-horizon tasks, including articulated object manipulation and cloth folding. Our results demonstrate that the synthesized skill library enables the system to transfer to novel tasks with decreasing human intervention, providing a steerable and data-efficient alternative to black-box
robot learning. Website: https://robo-architect.github.io/
Read the full abstract ▾
All authors Daphne Chen, Archit Ritesh Jain, Eric Goossen, Emma Romig, Michael Murray, Nick Walker, Maya Cakmak
Artificial Intelligence · Cross-listed from cs.LG
Scale Weight Decay and Train Better
Anuj Apte
The discovery of scaling laws has motivated training neural networks on ever increasing quantities of data. This is typically done with a constant decoupled weight decay which causes the network weights to shrink steadily over the course of training. Taking inspiration from the Robbins–Monro conditions, we propose to scale weight decay by the fraction of the peak learning rate $\eta/\eta_{\max}$. We prove that this scaled weight decay preserves the asymptotic stationarity guarantees of the corresponding unregularized methods for both
stochastic gradient descent and the non-Euclidean spectral optimizer
Muon, thereby avoiding the additional asymptotic bias introduced by constant decoupled weight decay. This retains the stability benefits of weight decay without changing the asymptotic optimization target. Using a steady-state analysis, we explain why under standard weight decay the weight norm shrinks steadily as training proceeds, whereas under scaled weight decay it settles to a roughly constant value. When applied to the training of mixture-of-experts models,
Muon with scaled weight decay (
Muon-SW) consistently outpaces
Muon with identical hyperparameters, reaching the same validation loss $\mathbf{30\%}$ faster at our largest scale across models from $72 - 930$ million parameters trained at $\sim 600$
tokens per active parameter. If this trend continues to hold, the method promises to substantially accelerate the pre-training of frontier models while requiring only a few lines of code to implement.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.SY
Outcome-Fair Restless Multi-Armed Bandits for Stochastic Deadline Scheduling
Shakti Sharma and Rahul Meshram
We study a restless multi-armed bandit (RMAB) problem for a
stochastic deadline scheduling application. RMAB problems are solved using the Whittle index policy. The goal in RMAB is to maximize the expected cumulative discounted reward maximization. The Whittle index policy maximizes reward, but is not fair among two classes. In this paper, we introduce
fairness criteria and study an outcome-fair model for RMAB which allows
fairness for jobs and users structurally disadvantaged demographic classes. We formulate an outcome fair
stochastic deadline scheduling problem as RMAB, and we develop the outcome fair Whittle index policy. We define a virtual queue mechanism that dynamically enforces long-term completion rate guaranties across demographic groups. We analyze a standard Whittle index policy and the outcome-fair index policy. We demonstrate the performance of our
algorithms with numerical examples. We compare policies—Whittle index policy (no
fairness), input-
fairness Whittle index policy, outcome fair Whittle index policy. We observe that the outcome-fair Whittle index policy provides better
fairness among classes compared to other policies. We demonstrate a trade off between
fairness and profit. This decreases as the server capacity increases.
Read the full abstract ▾
Artificial Intelligence
Training Language Models to Cooperate with Inference-Time Controllers
Moumita Choudhury, Vanshaj Khattar, Jing Liu et al. (+4 more)
Large
language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize
reasoning. Existing post-training methods, however, typically optimize for a single fixed interaction pattern, despite real deployments relying on diverse controllers such as Chain-of-Thought, self-consistency, debate, planning, and verification pipelines. This creates a training–deployment mismatch and limits transfer to new workflows. We introduce CALM (Controller-Aware
Language Models), a post-training framework that explicitly places controllers in the training loop. We formulate controller-aware post-training as multi-task reinforcement learning over controller-induced interaction protocols, where controllers are compositions of reusable local
reasoning modules. This structure also induces a module-level decomposition of mixed-controller training under a turn-level GRPO objective, enabling a systematic study of controller and module-aware training strategies. We evaluate CALM on held-out controller compositions and broader controller shifts, showing that controller-aware post-training improves generalization across inference-time workflows beyond single-controller optimization.
Read the full abstract ▾
All authors Moumita Choudhury, Vanshaj Khattar, Jing Liu, Toshiaki Koike-Akino, Ankush Chakrabarty, Shlomo Zilberstein, Ye Wang
Artificial Intelligence · Cross-listed from cs.LG
WISERouter: LLM Routing with Workload Budget Constraint
Yifei Li, Zihui Gao and Laks V.S. Lakshmanan
Large
language models (LLMs) achieve impressive performance across multiple domains, but using the most capable model for every query is prohibitive at scale. LLM routing exploits diversity in model capability and cost by assigning each query to a suitable model to balance utility and budget. Current methods have two limitations: (i) they either use heuristics that do not always enforce the budget constraint or impose a fixed per-query budget that cannot adapt across the workload and leads to suboptimal performance; (ii) they require supervised learning on a dense
dataset with statistics for every query-model pair, which is expensive to collect. To address these challenges, we formulate LLM routing as a constrained contextual multi-armed bandit problem and introduce WISERouter (WR for short), a framework that supports offline learning from historical interactions as well as online learning with exploration. We further prove that WR-Online achieves a sublinear regret bound of $O(\sqrt{T})$ over a time horizon $T$. Empirical results on RouterBench and SWE-Bench demonstrate that (i) WR-Offline surpasses existing baselines in performance under a fixed budget and adheres more closely to budget constraints, and (ii) WR-Online achieves comparable performance to the baselines, while using substantially less exploration data.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IR
Escaping the Euclidean Void: Manifold-Informed Flow Matching for Sequential Recommendation
Dengzhao Fang, Jingtong Gao, Yu Li et al. (+2 more)
Conventional recommenders capture users' preferences by optimizing observed user-item relations, whereas continuous generative recommendation additionally learns the trajectory of synthesizing a target item. Flow matching drives this process by gradually shaping initial noise into a definitive next-item representation through intermediate states in a continuous
embedding space. However, item catalogs are discrete and sparsely supported, meaning even a straight Euclidean path can cross continuous regions that contain little evidence of valid item semantics. Formalizing this failure as the Euclidean void, we propose MIRAGE, a
Manifold-Informed Rectification framework for Accelerated Generation of
Embeddings in sequential recommendation, which rectifies the learned
embedding geometry around an unchanged straight probability path. By leveraging an item co-occurrence graph as a proxy for the underlying semantic
manifold, MIRAGE aligns interpolated path states with local anchors, reorganizing the
embedding space to ground the trajectory in valid item support. MIRAGE retains the original probability path and uses the graph only during training, thereby enabling accurate and efficient one-step inference. Extensive experiments on four real-world
datasets reveal that MIRAGE consistently outperforms state-of-the-art baselines, effectively boosting performance on sparsely observed targets while achieving robust overall accuracy. Our code will be made publicly available upon publication.
Read the full abstract ▾
All authors Dengzhao Fang, Jingtong Gao, Yu Li, Xiangyu Zhao, Yi Chang
Artificial Intelligence · Cross-listed from cs.CY
AI Strategy: How to Choose What AI Product to Implement
Foster Provost and Panos Ipeirotis
Firms struggle to choose AI projects that pay off: two projects can look equally promising to smart, motivated stakeholders and yet deserve opposite decisions. At the residential real-estate brokerage Compass, one AI product (Likely-to-Sell recommendations) flagged sales outreach opportunities and went on to account for nine figures in annual gross commission revenue. Another championed AI product (a Time-on-
Market pricing tool) was rightly shelved. A simple ROI estimate could not distinguish the two. We present expected ROI (eROI), a framework that decomposes each bet into three components and rates them separately: Value if Successful, Likelihood of Success, and Investment Required. Each maps to a question executives can answer before building: How valuable would it be if it worked? How likely is it to work? And what would it cost to implement? Separating the three breaks a common catch-22: teams cannot estimate ROI until they know whether a project will work, yet cannot know whether it will work without building it. Judging Value if Successful on its own dissolves the loop, letting a team argue that a product would be valuable if it worked while it weighs how likely that is. The framework also asks, before ranking anything, whether there are enough good ideas on the table. After ranking, it guides assembling a portfolio of bets rather than funding only the single top-ranked project. We illustrate eROI on Compass's candidate AI products. Precise ROI estimates are hard to make given the inherent uncertainty of AI projects. Coarse business-level ratings of the three components are enough to tell strong bets from weak ones.
Read the full abstract ▾