It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs ...
Speculative decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose outputs that a stronger target model verif...
The LLM-as-a-judge paradigm has become the operational backbone of automated AI evaluation pipelines, yet rests on an unverified assumption: that judges evaluat...
Humor is one of the few cognitive tasks where getting the reasoning right matters as much as getting the answer right. While recent work evaluates humor underst...
Machine learning in high-stakes domains such as healthcare requires not only strong predictive performance but also reliable uncertainty quantification (UQ) to ...
Simulating group-level user behavior enables scalable counterfactual evaluation of merchant strategies without costly online experiments. However, building a tr...
Sparse attention has been proposed as a way to alleviate the quadratic cost of transformers, a central bottleneck in long-context training. A promising line of ...
LLMs are proving to be adept at machine translation although due to their generative nature they may at times overgenerate in various ways. These overgeneration...
This beta technical report asks how reusable experience should be represented so that it can function as effective test-time control and as a substrate for iter...
Overview Most document workflows break at the same place: a contract is uploaded, then downloaded, and a human spends 30–60 minutes scanning for key clauses, r...
Spatial reasoning over three-dimensional scenes is a core capability for embodied intelligence, yet continuous model improvement remains bottlenecked by the cos...
While reinforcement learning with verifiable rewards (RLVR) significantly enhances LLM reasoning by optimizing the conditional distribution P(y|x), its potentia...
Evaluating LLMs is challenging, as benchmark scores often fail to capture models' real-world usefulness. Instead, users often rely on ``vibe-testing'': informal...
Rhetorical questions are asked not to seek information but to persuade or signal stance. How large language models internally represent them remains unclear. We...
LLM reasoning traces suffer from complex flaws -- *Step Internal Flaws* (logical errors, hallucinations, etc.) and *Step-wise Flaws* (overthinking, underthinkin...
While Large Language Models (LLMs) have empowered AI research agents to perform isolated scientific tasks, automating complex, real-world workflows, such as LLM...
GUI grounding, which localizes interface elements from screenshots given natural language queries, remains challenging for small icons and dense layouts. Test-t...
Large Language Models (LLMs) are now capable of generating highly fluent, human-like text. They enable many applications, but also raise concerns such as large ...
Post-training adaptation of language models is commonly achieved through parameter updates or input-based methods such as fine-tuning, parameter-efficient adapt...
Deep search agents have emerged as a promising paradigm for addressing complex information-seeking tasks, but their training remains challenging due to sparse r...
Diffusion language models have recently emerged as a leading alternative to standard language models, due to their ability for bidirectional attention and paral...
Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static plannin...
Large Language Models (LLMs) and Vision-Language Models (VLMs) increasingly generate indoor scenes through intermediate structures such as layouts and scene gra...
Autonomous AI research has advanced rapidly, but long-horizon ML research engineering remains difficult: agents must sustain coherent progress across task compr...
On-policy distillation (OPD) has become a core technique in the post-training of large language models, yet its training dynamics remain poorly understood. This...
Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness when trivially constrained? We show that simpl...
Large Language Models (LLMs) are increasingly integrated into real-world decision-making, including in the domain of public policy. Yet, their ability to compre...
Speculative decoding accelerates autoregressive language models by using a lightweight drafter to propose multiple future tokens, which the target model then ve...
Optical character recognition (OCR) has advanced rapidly with the rise of vision-language models, yet evaluation has remained concentrated on a small cluster of...
Speech-to-speech language models have recently emerged to enhance the naturalness of conversational AI. In particular, full-duplex models are distinguished by t...
Metonymy and metaphor often co-occur in natural language, yet computational work has studied them largely in isolation. We introduce a framework that transforms...
Multilingual benchmarks guide the development of frontier models. Yet multilingual evaluations reported by frontier models are structured similar to popular rea...
Large language models (LLMs) can generate code from natural language, but the extent to which they capture intended program behavior remains unclear. Executable...
To identify safety violations, auditors often search over large sets of agent traces. This search is difficult because failures are often rare, complex, and som...
Natural language processing (NLP) and speech technologies have made significant progress in recent years; however, they remain largely focused on standardized l...
Using psychological constructs such as the Big Five, large language models (LLMs) can imitate specific personality profiles and predict a user's personality. Wh...
With the recent progress of Large Language Models (LLMs), there is a growing interest in applying these models to solve complex and challenging problems. Modern...
Recently, large language models (LLMs) are capable of generating highly fluent textual content. While they offer significant convenience to humans, they also in...
GUI agents drive applications through their visual interfaces instead of programmatic APIs, interacting with arbitrary software via taps, swipes, and keystrokes...
Contemporary large language models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in specialized domains like mathematics and physics....
We study parallel test-time scaling for long-horizon agentic tasks such as agentic search and deep research, where multiple rollouts are generated in parallel a...
Language change both reflects and shapes social processes, and the semantic evolution of foundational concepts provides a measurable trace of historical and soc...
Continuous diffusion models have achieved strong performance across domains such as images. However, in language modeling, prior continuous diffusion language m...
We present this as a negative result with an explanatory mechanism, not as a formal upper bound. Predictive coding networks (PCNs) admit a K-way energy probe in...
Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass the...
Evidence-grounded reasoning requires more than attaching retrieved text to a prediction: a model should make decisions that depend on whether the provided evide...
Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition. One plausible contributing fa...
Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, whic...
