Robust Learning of a Group DRO Neuron
arXiv:2601.18115v2 Announce Type: replace Abstract: We study the problem of learning a single neuron under standard squared loss in the presence of arbitrary label noise and group-level distributional
Knowledge catalogue
arXiv:2601.18115v2 Announce Type: replace Abstract: We study the problem of learning a single neuron under standard squared loss in the presence of arbitrary label noise and group-level distributional
arXiv:2606.00902v1 Announce Type: new Abstract: General-purpose VLMs remain unreliable for biomedical research because valid answers in scientific papers depend on evidence split across figures, table
arXiv:2606.01504v1 Announce Type: cross Abstract: Semantic retrieval in e-commerce must handle short, noisy, and colloquial queries over large product catalogs with fine-grained attribute distinctions
arXiv:2606.02041v1 Announce Type: new Abstract: Large language models increasingly stream long, reasoning-intensive responses in real time, making when to moderate as critical as whether to moderate.
arXiv:2606.00462v1 Announce Type: cross Abstract: Short-form text rewriting is a constrained variant of paraphrasing in which limited context and high semantic density leave little room for variation.
arXiv:2606.01723v1 Announce Type: cross Abstract: Real-world regression often exhibits shortcuts: attributes that are spuriously correlated with continuous targets in training, yet unreliable under de
arXiv:2606.01246v1 Announce Type: new Abstract: Text-to-SQL on complex schemas is unreliable on a single pass, so recent systems generate multiple SQL candidates and let voting filter out errors. Yet
arXiv:2606.02548v1 Announce Type: new Abstract: Word Error Rate (WER) is the dominant metric for automatic speech recognition (ASR), but it can overestimate errors when references and hypotheses encod
arXiv:2606.01479v1 Announce Type: new Abstract: Integrating large language models (LLMs) into text-to-speech (TTS) systems has improved speech expressiveness, yet interpretable emotional control remai
arXiv:2606.00762v1 Announce Type: new Abstract: Autonomous target search is crucial for deploying Micro Aerial Vehicles (MAVs) in emergency response and rescue missions. Existing approaches either foc
arXiv:2606.00825v1 Announce Type: new Abstract: AI glasses present a compelling platform for AI agents to serve as personalized memory assistants. To be genuinely useful, such systems must move beyond
arXiv:2602.23866v2 Announce Type: replace-cross Abstract: Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training
arXiv:2510.23379v2 Announce Type: replace-cross Abstract: We investigate a relatively under-explored class of hybrid neurosymbolic models that integrate symbolic learning with neural reasoning to cons
arXiv:2606.01820v1 Announce Type: new Abstract: Fine-grained morphosyntactic error annotation is important in clinical and developmental language research, yet it is labour-intensive, expert-dependent
arXiv:2606.01613v1 Announce Type: cross Abstract: This paper presents an agentic retrieval-augmented generation (RAG) framework for domain-specific technical reasoning support, instantiated over a cur
arXiv:2606.01456v1 Announce Type: cross Abstract: Large language models are increasingly deployed as advisors whose objective is not aligned with the user's: recommenders optimize for engagement, sale
arXiv:2606.01322v1 Announce Type: cross Abstract: Safety evaluation of Large Language Models (LLMs) remains heavily English-centric, leaving Low-Resource Languages (LRLs), particularly African ones, c
arXiv:2606.01394v1 Announce Type: new Abstract: Systematic characterization of drug-disease relationships is essential for drug discovery and repurposing, yet is hindered by the heterogeneity and rapi
arXiv:2602.03685v2 Announce Type: replace-cross Abstract: Training large language models (LLMs) is computationally expensive, partly because the loss exhibits slow power-law convergence whose origin r
arXiv:2506.13702v4 Announce Type: replace-cross Abstract: Single-trajectory preference optimization methods learn from datasets of ((prompt, response, reward)) tuples, offering a practical alternative
arXiv:2606.00735v1 Announce Type: cross Abstract: In distributed Mixture-of-Experts (MoE) inference, input-dependent token routing interacts with GPU performance variability to create persistent strag
arXiv:2606.02273v1 Announce Type: new Abstract: Understanding subtle driver actions is essential for building reliable driver monitoring systems. Existing visionlanguage models (VLMs) are trained on g
arXiv:2606.01624v1 Announce Type: new Abstract: Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs), yet veri
arXiv:2606.02245v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) typically assumes that external knowledge is free, but many high-quality sources are paywalled, licensed, restricte
arXiv:2606.02060v1 Announce Type: new Abstract: Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis. Evaluation based on final ans
arXiv:2605.31080v1 Announce Type: cross Abstract: Blind and low-vision (BLV) audiences remain underserved by visual art descriptions, particularly across languages and in museum settings where privacy
arXiv:2605.30582v1 Announce Type: new Abstract: While platforms like Google Scholar and Semantic Scholar track citations for academic papers, no comparable infrastructure exists for monitoring dataset
arXiv:2605.30914v1 Announce Type: new Abstract: Automated formal verification remains challenging for large language models because data for proof assistants and verification-aware languages is scarce
arXiv:2605.31468v1 Announce Type: new Abstract: Scientific research has traditionally been human-intensive, requiring researchers to coordinate literature, ideas, experiments, manuscripts, and review
arXiv:2605.30826v1 Announce Type: cross Abstract: Biomedical NER is deceptively simple for modern LLMs: plausible biomedical mentions are easy to surface, but corpus-convention correctness depends on
arXiv:2605.30613v1 Announce Type: cross Abstract: Over the past year, prompt caching in Large Language Models (LLMs) has become increasingly more popular across inference APIs. Prompt caching helps sa
arXiv:2605.30394v1 Announce Type: cross Abstract: This paper introduces Code Bench, a benchmark capable of evaluating Large Language Models (LLMs) concise code generation abilities in 60 programming l
arXiv:2605.30981v1 Announce Type: new Abstract: Autoregressive language models frequently degrade during long-horizon generation, producing repetitive text, losing instruction adherence, and exhibitin
Connecting agents directly to Snowflake, Slack, or BigQuery via MCP/CLIs is a multi-token disaster. They default to brute-force exploration, firing 20-30 tool calls just to rediscover context on every
arXiv:2601.06453v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly grounded in sensor data to perceive and reason about human physiology and the physical world. However,
arXiv:2605.30808v1 Announce Type: cross Abstract: Preference alignment is a crucial post-training step for large language models (LLMs) to ensure their outputs align with human values. However, post-t
arXiv:2605.31293v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently memorize sensitive training data thereby creating significant privacy and copyright risks. Addressing these risk
arXiv:2605.30934v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit systematic differences in moral reasoning across languages, yet the source of this variation remains unclear. We
arXiv:2605.30415v1 Announce Type: cross Abstract: We investigate how domain adaptation reshapes explanatory behavior in language models using historical cosmology as a controlled setting. In Phase 1,
arXiv:2605.31228v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models
arXiv:2603.19262v2 Announce Type: replace-cross Abstract: Large language models increasingly rely on inference-time procedures such as chain-of-thought reasoning, self-refinement, retrieval augmentati
arXiv:2605.30654v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as conversational partners for companionship, emotional disclosure, and interpersonal advice, but t
arXiv:2605.30771v1 Announce Type: new Abstract: AI agents that persist across sessions need memory they can retrieve, audit, update, and erase. Existing memory systems often collapse source evidence,
arXiv:2605.31446v1 Announce Type: cross Abstract: Aspect Sentiment Triplet Extraction (ASTE) aims to identify aspect terms, opinion terms, and sentiment polarities as structured triplets, providing es
arXiv:2601.19936v2 Announce Type: replace-cross Abstract: The opacity of massive pretraining corpora in Large Language Models (LLMs) raises significant privacy and copyright concerns, making pretraini
arXiv:2605.30529v1 Announce Type: cross Abstract: Sentence-embedding models for semantic search are overwhelmingly developed and evaluated on English corpora. When applied to clinical retrieval in oth
arXiv:2605.30740v1 Announce Type: cross Abstract: Articulated object manipulation is a unique challenge for service robots. Existing methods employ end-to-end policy learning, visionmotion planning, a
arXiv:2605.30680v1 Announce Type: new Abstract: Healthcare mechanisms are inseparable from the strategic provider response they induce: existing healthcare AI benchmarks hold this response fixed and s
arXiv:2605.31000v1 Announce Type: cross Abstract: Training Large Language Models (LLMs) on heterogeneous clusters presents significant challenges for collective communication, as hardware from multipl
arXiv:2508.08204v2 Announce Type: replace-cross Abstract: There has been much recent interest in evaluating large language models for uncertainty calibration to facilitate model control and modulate u
i know it's backwards order, but experiment #2: https://x.com/ActiveGraphAI/status/2061106299748909090?s=20 [New Technical Blog Post] In our second longmemeval experiment, we introduce semantic ingest
arXiv:2605.30589v1 Announce Type: cross Abstract: U.S. immigration law spans thousands of pages of official policy, federal regulations, and procedural guidance that change frequently and carry high s
arXiv:2605.30615v1 Announce Type: new Abstract: In selective classification, a model predicts the labels of data samples where it is confident, and abstains from predicting labels for samples on which
arXiv:2605.31278v1 Announce Type: new Abstract: Reliable evaluation of agentic systems requires unbiased estimates with valid uncertainty, but standard practice navigates between costly human annotati
arXiv:2605.30903v1 Announce Type: cross Abstract: Inverse reinforcement learning (IRL) typically assumes demonstrations from a single optimal demonstrator, but in many applications data come from mult
arXiv:2605.31099v1 Announce Type: cross Abstract: Science news is an important medium to communicate discoveries between the research communities and the public. Yet, most metrics for generated or sum
arXiv:2605.31480v1 Announce Type: new Abstract: Do neural models, such as Large Language Models, genuinely acquire compositional abilities for interpretation of natural language? When we talk about se
arXiv:2412.18134v4 Announce Type: replace Abstract: Randomized self-reductions (RSRs) express f(x) using f evaluated at random correlated points, enabling self-correcting programs, instance-hiding pro
arXiv:2509.16187v3 Announce Type: replace-cross Abstract: Code translation transforms source code from one programming language (PL) to another. Validating the functional equivalence of translation an
arXiv:2605.30727v1 Announce Type: new Abstract: Deep research agents increasingly combine private local documents with external tools like web retrieval, creating a privacy risk: an agent's external q