Knowledge catalogue
arXiv:2607.21756v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in database-backed applications to classify tuples, filter records using semantic predicates, extra
arXiv:2607.21635v1 Announce Type: new Abstract: Personal agents maintain memories, learned skills, tool configurations, and policy state that evolve with each user. Existing agent benchmarks often eva
arXiv:2607.21292v1 Announce Type: new Abstract: We present a structured large-language-model-driven workflow for automated multi-variable control design from dynamic process models. The workflow decom
arXiv:2607.20768v1 Announce Type: cross Abstract: Majority voting over LLMs is widely assumed to benefit from diversity, and diversity measures are used to choose which models to combine. We ask wheth
arXiv:2607.20441v1 Announce Type: new Abstract: Every information ecosystem produces beliefs that shape strategic decisions. Both human analysts and AI systems inherit the blind spots of their informa
arXiv:2607.21558v1 Announce Type: new Abstract: Building socially calibrated large language models, which can learn from others without simply yielding to them, requires more than reducing sycophancy
arXiv:2607.20444v1 Announce Type: cross Abstract: Large language models (LLMs) can produce deceptive responses: outputs that mislead users in service of a contextually or experimentally induced goal.
arXiv:2607.20469v1 Announce Type: new Abstract: Large language models (LLMs) handle many tasks with one set of parameters, but under KV-cached inference it is unclear what task-general structure, if a
arXiv:2607.20487v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to answer questions about political information, including in election-adjacent information settings
arXiv:2607.20757v1 Announce Type: cross Abstract: Transformers are known to have internal continuous symmetries that leave outputs invariant, while modifying quantization. GaugeQuant leverages this in
arXiv:2607.20435v1 Announce Type: cross Abstract: Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace the text they generate by embedding text watermar
arXiv:2607.21180v1 Announce Type: new Abstract: Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verba
arXiv:2607.21072v1 Announce Type: new Abstract: Spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world. Many spatial tasks a
arXiv:2607.09999v2 Announce Type: replace Abstract: We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved. Using a six-catego
arXiv:2607.21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations. To evaluate unlearning e
arXiv:2607.19629v1 Announce Type: cross Abstract: Large language models operating in emotionally sensitive contexts face a structural trilemma: when users in vulnerable states request information that
arXiv:2607.20083v1 Announce Type: cross Abstract: Post-training with evaluator feedback on policy-induced samples serves as a major mechanism for improving large language models. As policies improve,
arXiv:2607.13315v2 Announce Type: replace Abstract: Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual sett
arXiv:2607.19408v1 Announce Type: new Abstract: Using Evolutionary Strategies (ES) for fine-tuning large language models is attractive because it is memory-efficient, parallel, and compatible with bla
arXiv:2607.13305v1 Announce Type: cross Abstract: Benchmark accuracy in video large language models (LLMs) is often treated as evidence of visual understanding. We audit this assumption across twenty
arXiv:2607.13069v1 Announce Type: new Abstract: Large language models produce chain-of-thought (CoT) reasoning that appears logically sound yet may not genuinely depend on its stated premises. We intr
arXiv:2601.20379v2 Announce Type: replace Abstract: Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption. Current test
arXiv:2607.08803v2 Announce Type: replace-cross Abstract: The push toward large language models for biology (BioLM) has created a need for training corpora that can endow models with a genuine underst
arXiv:2510.26707v2 Announce Type: replace-cross Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw
arXiv:2607.12338v1 Announce Type: new Abstract: Agent benchmarks often compare two agents after all tasks have run, but costly evaluations make partial runs tempting. A task fraction alone does not sh
arXiv:2607.12790v1 Announce Type: new Abstract: Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable e
Very impressive release by the PrismML team. 1-bit quantization shrinks it from 54GB to just 3.8GB (-93%), while retaining 90% of its intelligence. - Collection on Hugging Face: https://huggingface.co
AI model co-design involves integrating model requirements into hardware planning to ensure memory hierarchies and networking stacks are purpose-built for specific systems . AI performance balances th
arXiv:2601.22448v2 Announce Type: replace-cross Abstract: RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cos
arXiv:2607.07964v1 Announce Type: new Abstract: Post-training quantization (PTQ) is a widely adopted technique for compressing large language models (LLMs) without retraining. Existing second-order PT
arXiv:2607.07719v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning adapts a large language model to one task cheaply, but across a task sequence LoRA-style methods keep stacking low-ran
Large language model training workloads increasingly encounter GPU memory limits before compute is fully utilized, with high-bandwidth memory capacity becoming the primary scaling bottleneck as model
arXiv:2607.08602v1 Announce Type: new Abstract: Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality. Current guidelines and staging systems provide co
arXiv:2607.08456v1 Announce Type: cross Abstract: A model should refuse two different things: answers it would get wrong, and questions it should not answer at all, such as unanswerable ones or ones r
arXiv:2607.08046v1 Announce Type: cross Abstract: Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully
arXiv:2607.07976v1 Announce Type: cross Abstract: Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, widely u
arXiv:2607.07103v1 Announce Type: new Abstract: Safe autonomous driving requires both rapid responses to common high-risk events and deeper reasoning over rare, extreme long-tail scenarios in traffic
arXiv:2607.07001v1 Announce Type: new Abstract: Anticipating human motion from an egocentric perspective is fundamental for proactive assistance in AR/VR, human-robot collaboration, and embodied AI. W
arXiv:2506.04985v2 Announce Type: replace Abstract: Large language models (LLMs) require substantial compute, and thus energy, at inference time. While quantizing weights and activations is effective
arXiv:2607.07144v1 Announce Type: new Abstract: The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through quantizati
arXiv:2607.06757v1 Announce Type: new Abstract: Agent-based modeling (ABM) has the capability to model millions of individuals and their interactions, which is useful for policy making. However, ABMs
arXiv:2510.25370v2 Announce Type: replace Abstract: Forecasting transformative technologies remains a critical but challenging task, particularly in fast-evolving domains such as Information and Commu
arXiv:2607.07557v1 Announce Type: new Abstract: One-shot pruning methods like Wanda and SparseGPT apply the same sparsity ratio to every layer of a transformer, ignoring known variation in layer impor
arXiv:2607.07184v1 Announce Type: cross Abstract: Pre-deployment safety evaluations aim to inform the downstream risks of releasing a new AI model. Yet most evaluations provide limited evidence about
arXiv:2607.06636v1 Announce Type: cross Abstract: Large language models frequently generate code that appears correct on typical inputs yet fails on edge cases, invalid inputs, and other specification
arXiv:2501.18784v5 Announce Type: replace Abstract: Heuristics are a central component of deterministic planning, particularly in domain-independent settings where general applicability is prioritized
arXiv:2607.05405v1 Announce Type: cross Abstract: To interact with users fairly and without stereotyping, AI models must display cultural competency, i.e., the ability to infer and adapt to a user's i
arXiv:2607.06326v1 Announce Type: new Abstract: Large language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-l
arXiv:2606.18181v2 Announce Type: replace-cross Abstract: Illegal, unreported, and unregulated fishing (IUU) traditionally refers to fishing activities that violate applicable laws or occur in areas t
arXiv:2607.05554v1 Announce Type: cross Abstract: Survey-style evaluations of large language models often treat a prompted response as a measure of a model's values or beliefs. This assumption is part
arXiv:2607.05863v1 Announce Type: new Abstract: Negotiation is a fundamental strategic interaction in management science, characterized by agents attempting to reach agreements while protecting privat
arXiv:2607.03876v1 Announce Type: new Abstract: With the rise of small quantized GGUF-based language models and their increasing use for on-device inference tasks, we have seen the growing need for an
arXiv:2607.02686v1 Announce Type: new Abstract: Reinforcement learning agents operating under partial observability must act on incomplete information, making them natural candidates for guidance from
arXiv:2607.03882v1 Announce Type: cross Abstract: LLMs are increasingly deployed as post-hoc explainers of AI-generated outputs, yet it remains unclear whether they can reliably communicate probabilis
arXiv:2607.02873v1 Announce Type: cross Abstract: Large language model agents driving security tool suites over the Model Context Protocol are increasingly common. Yet the factors that bound their cap
arXiv:2607.03886v1 Announce Type: cross Abstract: Sponsored search plays a crucial role as a revenue stream for search engines, wherein advertisers competitively bid on keywords that align with the us
arXiv:2607.03870v1 Announce Type: new Abstract: As LLMs generate increasingly long outputs, effective uncertainty estimation must identify errors at fine-grained levels rather than discard entire resp
arXiv:2607.04394v1 Announce Type: new Abstract: AI reasoning has become a central focus in contemporary artificial intelligence, largely driven by the success of large language models. However, mathem
arXiv:2607.02879v1 Announce Type: new Abstract: Current benchmarks for evaluating large language models (LLMs) in medical calculation are largely based on simplified settings, where each patient case
arXiv:2607.03948v1 Announce Type: new Abstract: We study the online routing problem in large language model serving, where requests arrive sequentially and must be dispatched to parallel decode worker