{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modelling/papers/74","list_of":"/task/language-modelling","task":"Language Modelling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":74,"pages_in_order":177,"rows_per_page":100,"rows":[7301,7400],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modelling","prev":"/task/language-modelling/papers/73","next":"/task/language-modelling/papers/75","papers":[{"url":null,"slug":"biomechgpt-towards-a-biomechanically-fluent","title":"BiomechGPT: Towards a Biomechanically Fluent Multimodal Foundation Model for Clinically Relevant Motion Tasks","date":"2025-05-24","arxiv_id":"2505.18465","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-a-functional-machine-translation","title":"Building a Functional Machine Translation Corpus for Kpelle","date":"2025-05-24","arxiv_id":"2505.18905","repositories_listed":0,"syntology":null},{"url":"/paper/chain-of-zoom-extreme-super-resolution-via","slug":"chain-of-zoom-extreme-super-resolution-via","title":"Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment","date":"2025-05-24","arxiv_id":"2505.18600","repositories_listed":0,"syntology":{"n":20,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/chain-of-zoom-extreme-super-resolution-via#ran","syntology_url":"https://syntology.ai/paper/2505.18600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18600"}},"official":null}},{"url":null,"slug":"disentangling-knowledge-representations-for","title":"Disentangling Knowledge Representations for Large Language Model Editing","date":"2025-05-24","arxiv_id":"2505.18774","repositories_listed":0,"syntology":null},{"url":null,"slug":"evdclip-improving-vision-language-retrieval","title":"EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models","date":"2025-05-24","arxiv_id":"2505.18594","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-compute-optimal-video-vision","title":"Inference Compute-Optimal Video Vision Language Models","date":"2025-05-24","arxiv_id":"2505.18855","repositories_listed":0,"syntology":null},{"url":null,"slug":"metatextgrad-automatically-optimizing","title":"metaTextGrad: Automatically optimizing language model optimizers","date":"2025-05-24","arxiv_id":"2505.18524","repositories_listed":0,"syntology":null},{"url":null,"slug":"msa-at-bea-2025-shared-task-disagreement","title":"MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors","date":"2025-05-24","arxiv_id":"2505.18549","repositories_listed":0,"syntology":null},{"url":null,"slug":"regen-multimodal-retrieval-embedded","title":"REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing","date":"2025-05-24","arxiv_id":"2505.18880","repositories_listed":0,"syntology":null},{"url":null,"slug":"skip-thinking-chunk-wise-chain-of-thought","title":"Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster","date":"2025-05-24","arxiv_id":"2505.18642","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthesizing-and-adapting-error-correction","title":"Synthesizing and Adapting Error Correction Data for Mobile Large Language Model Applications","date":"2025-05-24","arxiv_id":"2505.18488","repositories_listed":0,"syntology":null},{"url":null,"slug":"elder-getting-efficient-llms-through-data","title":"ELDeR: Getting Efficient LLMs through Data-Driven Regularized Layer-wise Pruning","date":"2025-05-23","arxiv_id":"2505.18232","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-as-user-daily-behavior","title":"Large language model as user daily behavior data generator: balancing population diversity and individual personality","date":"2025-05-23","arxiv_id":"2505.17615","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-systems-for-misinformation","title":"Multi-agent Systems for Misinformation Lifecycle : Detection, Correction And Source Identification","date":"2025-05-23","arxiv_id":"2505.17511","repositories_listed":0,"syntology":null},{"url":null,"slug":"nsnquant-a-double-normalization-approach-for","title":"NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache","date":"2025-05-23","arxiv_id":"2505.18231","repositories_listed":0,"syntology":null},{"url":null,"slug":"plan-r1-safe-and-feasible-trajectory-planning","title":"Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling","date":"2025-05-23","arxiv_id":"2505.17659","repositories_listed":0,"syntology":null},{"url":null,"slug":"qwenlong-cprs-towards-infty-llms-with-dynamic","title":"QwenLong-CPRS: Towards $\\infty$-LLMs with Dynamic Context Optimization","date":"2025-05-23","arxiv_id":"2505.18092","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-generation-based-large","title":"Retrieval Augmented Generation-based Large Language Models for Bridging Transportation Cybersecurity Legal Knowledge Gaps","date":"2025-05-23","arxiv_id":"2505.18426","repositories_listed":0,"syntology":null},{"url":null,"slug":"selection-mechanisms-for-sequence-modeling","title":"Selection Mechanisms for Sequence Modeling using Linear State Space Models","date":"2025-05-23","arxiv_id":"2505.17932","repositories_listed":0,"syntology":null},{"url":null,"slug":"simulating-macroeconomic-expectations-using","title":"Simulating Macroeconomic Expectations using LLM Agents","date":"2025-05-23","arxiv_id":"2505.17648","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectralds-provable-distillation-for-linear","title":"SpectraLDS: Provable Distillation for Linear Dynamical Systems","date":"2025-05-23","arxiv_id":"2505.17868","repositories_listed":0,"syntology":null},{"url":null,"slug":"taming-llms-with-negative-samples-a-reference","title":"Taming LLMs with Negative Samples: A Reference-Free Framework to Evaluate Presentation Content with Actionable Feedback","date":"2025-05-23","arxiv_id":"2505.18240","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-with-trained-embeddings-provably","title":"Attention with Trained Embeddings Provably Selects Important Tokens","date":"2025-05-22","arxiv_id":"2505.17282","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-correlation-towards-causal-large","title":"Beyond Correlation: Towards Causal Large Language Model Agents in Biomedicine","date":"2025-05-22","arxiv_id":"2505.16982","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-graph-model-cgm-a-graph-integrated-large","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","date":"2025-05-22","arxiv_id":"2505.16901","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctrap-embedding-collapse-trap-to-safeguard","title":"CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning","date":"2025-05-22","arxiv_id":"2505.16559","repositories_listed":0,"syntology":null},{"url":null,"slug":"deeprec-towards-a-deep-dive-into-the-item","title":"DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based Recommendation","date":"2025-05-22","arxiv_id":"2505.16810","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-first-language-model-inference-models","title":"Edge-First Language Model Inference: Models, Metrics, and Tradeoffs","date":"2025-05-22","arxiv_id":"2505.16508","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-large-language-model-with","title":"Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering","date":"2025-05-22","arxiv_id":"2505.16591","repositories_listed":0,"syntology":null},{"url":null,"slug":"incentivizing-dual-process-thinking-for","title":"Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning","date":"2025-05-22","arxiv_id":"2505.16315","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-sequence-classification-with","title":"Incremental Sequence Classification with Temporal Consistency","date":"2025-05-22","arxiv_id":"2505.16548","repositories_listed":0,"syntology":null},{"url":null,"slug":"inferencedynamics-efficient-routing-across","title":"INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling","date":"2025-05-22","arxiv_id":"2505.16303","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-empowered-interactive","title":"Large Language Model-Empowered Interactive Load Forecasting","date":"2025-05-22","arxiv_id":"2505.16577","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-principle-discovery-for-language-model","title":"Latent Principle Discovery for Language Model Self-Improvement","date":"2025-05-22","arxiv_id":"2505.16927","repositories_listed":0,"syntology":null},{"url":null,"slug":"llada-v-large-language-diffusion-models-with","title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","date":"2025-05-22","arxiv_id":"2505.16933","repositories_listed":0,"syntology":null},{"url":null,"slug":"mechanistic-understanding-and-mitigation-of","title":"Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models","date":"2025-05-22","arxiv_id":"2505.16538","repositories_listed":0,"syntology":null},{"url":null,"slug":"mm-moviedubber-towards-multi-modal-learning","title":"MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing","date":"2025-05-22","arxiv_id":"2505.16279","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-multilingual-encoder-language-model","title":"On Multilingual Encoder Language Model Compression for Low-Resource Languages","date":"2025-05-22","arxiv_id":"2505.16956","repositories_listed":0,"syntology":null},{"url":null,"slug":"plan-and-budget-effective-and-efficient-test","title":"Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning","date":"2025-05-22","arxiv_id":"2505.16122","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-to-large-generalization-data-influences","title":"Small-to-Large Generalization: Data Influences Models Consistently Across Scale","date":"2025-05-22","arxiv_id":"2505.16260","repositories_listed":0,"syntology":null},{"url":null,"slug":"tensorar-refinement-is-all-you-need-in","title":"TensorAR: Refinement is All You Need in Autoregressive Image Generation","date":"2025-05-22","arxiv_id":"2505.16324","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-dialogue-agents-with-global-feedback","title":"Aligning Dialogue Agents with Global Feedback via Large Language Model Reward Decomposition","date":"2025-05-21","arxiv_id":"2505.15922","repositories_listed":0,"syntology":null},{"url":null,"slug":"any-large-language-model-can-be-a-reliable","title":"Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector","date":"2025-05-21","arxiv_id":"2505.17100","repositories_listed":0,"syntology":null},{"url":null,"slug":"cp-llm-context-and-pixel-aware-large-language","title":"CP-LLM: Context and Pixel Aware Large Language Model for Video Quality Assessment","date":"2025-05-21","arxiv_id":"2505.16025","repositories_listed":0,"syntology":null},{"url":null,"slug":"debate-train-evolve-self-evolution-of","title":"DEBATE, TRAIN, EVOLVE: Self Evolution of Language Model Reasoning","date":"2025-05-21","arxiv_id":"2505.15734","repositories_listed":0,"syntology":null},{"url":null,"slug":"denoising-concept-vectors-with-sparse","title":"Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering","date":"2025-05-21","arxiv_id":"2505.15038","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-vs-autoregressive-language-models-a","title":"Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective","date":"2025-05-21","arxiv_id":"2505.15045","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-and-direct-duplex-modeling-for","title":"Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model","date":"2025-05-21","arxiv_id":"2505.15670","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensembling-sparse-autoencoders","title":"Ensembling Sparse Autoencoders","date":"2025-05-21","arxiv_id":"2505.16077","repositories_listed":0,"syntology":null},{"url":null,"slug":"forging-time-series-with-language-a-large","title":"Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation","date":"2025-05-21","arxiv_id":"2505.17103","repositories_listed":0,"syntology":null},{"url":null,"slug":"internal-and-external-impacts-of-natural","title":"Internal and External Impacts of Natural Language Processing Papers","date":"2025-05-21","arxiv_id":"2505.16061","repositories_listed":0,"syntology":null},{"url":null,"slug":"likelihood-variance-as-text-importance-for","title":"Likelihood Variance as Text Importance for Resampling Texts to Map Language Models","date":"2025-05-21","arxiv_id":"2505.15428","repositories_listed":0,"syntology":null},{"url":null,"slug":"listen-to-the-context-towards-faithful-large","title":"Listen to the Context: Towards Faithful Large Language Models for Retrieval Augmented Generation on Climate Questions","date":"2025-05-21","arxiv_id":"2505.15633","repositories_listed":0,"syntology":null},{"url":null,"slug":"mechanistic-evaluation-of-transformers-and","title":"Mechanistic evaluation of Transformers and state space models","date":"2025-05-21","arxiv_id":"2505.15105","repositories_listed":0,"syntology":null},{"url":null,"slug":"miku-pal-an-automated-and-standardized-multi","title":"MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling","date":"2025-05-21","arxiv_id":"2505.15772","repositories_listed":0,"syntology":null},{"url":null,"slug":"revealing-language-model-trajectories-via","title":"Revealing Language Model Trajectories via Kullback-Leibler Divergence","date":"2025-05-21","arxiv_id":"2505.15353","repositories_listed":0,"syntology":null},{"url":null,"slug":"segmentation-variant-codebooks-for","title":"Segmentation-Variant Codebooks for Preservation of Paralinguistic and Prosodic Information","date":"2025-05-21","arxiv_id":"2505.15667","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-give-associative-thinking-from-limited","title":"Self-GIVE: Associative Thinking from Limited Structured Knowledge for Enhanced Large Language Model Reasoning","date":"2025-05-21","arxiv_id":"2505.15062","repositories_listed":0,"syntology":null},{"url":null,"slug":"short-range-dependency-effects-on-transformer","title":"Short-Range Dependency Effects on Transformer Instability and a Decomposed Attention Solution","date":"2025-05-21","arxiv_id":"2505.15548","repositories_listed":0,"syntology":null},{"url":"/paper/trajectory-bellman-residual-minimization-a","slug":"trajectory-bellman-residual-minimization-a","title":"Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning","date":"2025-05-21","arxiv_id":"2505.15311","repositories_listed":0,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/trajectory-bellman-residual-minimization-a#ran","syntology_url":"https://syntology.ai/paper/2505.15311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15311"}},"official":null}},{"url":null,"slug":"your-language-model-can-secretly-write-like","title":"Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors","date":"2025-05-21","arxiv_id":"2505.15337","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-journalistic-questions-a-new-method","title":"Automated Journalistic Questions: A New Method for Extracting 5W1H in French","date":"2025-05-20","arxiv_id":"2505.14804","repositories_listed":0,"syntology":null},{"url":null,"slug":"cafes-a-collaborative-multi-agent-framework","title":"CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring","date":"2025-05-20","arxiv_id":"2505.13965","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctrldiff-boosting-large-diffusion-language","title":"CtrlDiff: Boosting Large Diffusion Language Models with Dynamic Block Prediction and Controllable Generation","date":"2025-05-20","arxiv_id":"2505.14455","repositories_listed":0,"syntology":null},{"url":null,"slug":"fuximt-sparsifying-large-language-models-for","title":"FuxiMT: Sparsifying Large Language Models for Chinese-Centric Multilingual Machine Translation","date":"2025-05-20","arxiv_id":"2505.14256","repositories_listed":0,"syntology":null},{"url":null,"slug":"hausanlp-current-status-challenges-and-future","title":"HausaNLP: Current Status, Challenges and Future Directions for Hausa Natural Language Processing","date":"2025-05-20","arxiv_id":"2505.14311","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-noise-robustness-of-llm-based-zero","title":"Improving Noise Robustness of LLM-based Zero-shot TTS via Discrete Acoustic Token Denoising","date":"2025-05-20","arxiv_id":"2505.13830","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-driven-distributed","title":"Large Language Model-Driven Distributed Integrated Multimodal Sensing and Semantic Communications","date":"2025-05-20","arxiv_id":"2505.18194","repositories_listed":0,"syntology":null},{"url":null,"slug":"mas-kcl-knowledge-component-graph-structure","title":"MAS-KCL: Knowledge component graph structure learning with large language model-based agentic workflow","date":"2025-05-20","arxiv_id":"2505.14126","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-agent-distillation-for-large","title":"Structured Agent Distillation for Large Language Model","date":"2025-05-20","arxiv_id":"2505.13820","repositories_listed":0,"syntology":null},{"url":null,"slug":"studying-the-role-of-input-neighbor-overlap","title":"Studying the Role of Input-Neighbor Overlap in Retrieval-Augmented Language Models Training Efficiency","date":"2025-05-20","arxiv_id":"2505.14309","repositories_listed":0,"syntology":null},{"url":null,"slug":"sudollm-on-multi-role-alignment-of-language","title":"sudoLLM : On Multi-role Alignment of Language Models","date":"2025-05-20","arxiv_id":"2505.14607","repositories_listed":0,"syntology":null},{"url":null,"slug":"trates-trait-specific-rubric-assisted-cross","title":"TRATES: Trait-Specific Rubric-Assisted Cross-Prompt Essay Scoring","date":"2025-05-20","arxiv_id":"2505.14577","repositories_listed":0,"syntology":null},{"url":null,"slug":"unigen-enhanced-training-test-time-strategies","title":"UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation","date":"2025-05-20","arxiv_id":"2505.14682","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-modeling-meets-remote-sensing","title":"Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives","date":"2025-05-20","arxiv_id":"2505.14361","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-decoding-token-efficient-inference-scaling","title":"A*-Decoding: Token-Efficient Inference Scaling","date":"2025-05-19","arxiv_id":"2505.13672","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-physics-inspired-optimizer-velocity","title":"A Physics-Inspired Optimizer: Velocity Regularized Adam","date":"2025-05-19","arxiv_id":"2505.13196","repositories_listed":0,"syntology":null},{"url":null,"slug":"cmlformer-a-dual-decoder-transformer-with","title":"CMLFormer: A Dual Decoder Transformer with Switching Point Learning for Code-Mixed Language Modeling","date":"2025-05-19","arxiv_id":"2505.12587","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-the-best-of-both-worlds-a-method","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","date":"2025-05-19","arxiv_id":"2505.13554","repositories_listed":0,"syntology":null},{"url":null,"slug":"ideal-data-equilibrium-adaptation-for-multi","title":"IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment","date":"2025-05-19","arxiv_id":"2505.12762","repositories_listed":0,"syntology":null},{"url":"/paper/krikri-advancing-open-large-language-models","slug":"krikri-advancing-open-large-language-models","title":"Krikri: Advancing Open Large Language Models for Greek","date":"2025-05-19","arxiv_id":"2505.13772","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-thinking-language-modeling-gap-in","title":"On the Thinking-Language Modeling Gap in Large Language Models","date":"2025-05-19","arxiv_id":"2505.12896","repositories_listed":0,"syntology":null},{"url":null,"slug":"orqa-a-benchmark-and-foundation-model-for","title":"ORQA: A Benchmark and Foundation Model for Holistic Operating Room Modeling","date":"2025-05-19","arxiv_id":"2505.12890","repositories_listed":0,"syntology":null},{"url":null,"slug":"r1dacted-investigating-local-censorship-in","title":"R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model","date":"2025-05-19","arxiv_id":"2505.12625","repositories_listed":0,"syntology":null},{"url":null,"slug":"resw-vl-representation-learning-for-surgical","title":"ReSW-VL: Representation Learning for Surgical Workflow Analysis Using Vision-Language Model","date":"2025-05-19","arxiv_id":"2505.13746","repositories_listed":0,"syntology":null},{"url":null,"slug":"sat2sound-a-unified-framework-for-zero-shot","title":"Sat2Sound: A Unified Framework for Zero-Shot Soundscape Mapping","date":"2025-05-19","arxiv_id":"2505.13777","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatialllm-from-multi-modality-data-to-urban","title":"SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence","date":"2025-05-19","arxiv_id":"2505.12703","repositories_listed":0,"syntology":null},{"url":null,"slug":"structure-aware-corpus-construction-and-user","title":"Structure-Aware Corpus Construction and User-Perception-Aligned Metrics for Large-Language-Model Code Completion","date":"2025-05-19","arxiv_id":"2505.13073","repositories_listed":0,"syntology":null},{"url":null,"slug":"surveillancevqa-589k-a-benchmark-for","title":"SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models","date":"2025-05-19","arxiv_id":"2505.12589","repositories_listed":0,"syntology":null},{"url":null,"slug":"tianyi-a-traditional-chinese-medicine-all","title":"Tianyi: A Traditional Chinese Medicine all-rounder language model and its Real-World Clinical Practice","date":"2025-05-19","arxiv_id":"2505.13156","repositories_listed":0,"syntology":null},{"url":null,"slug":"tinyalign-boosting-lightweight-vision","title":"TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks","date":"2025-05-19","arxiv_id":"2505.12884","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlc-fusion-vision-language-conditioned-sensor","title":"VLC Fusion: Vision-Language Conditioned Sensor Fusion for Robust Object Detection","date":"2025-05-19","arxiv_id":"2505.12715","repositories_listed":0,"syntology":null},{"url":null,"slug":"vocalagent-large-language-models-for-vocal","title":"VocalAgent: Large Language Models for Vocal Health Diagnostics with Safety-Aware Evaluation","date":"2025-05-19","arxiv_id":"2505.13577","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-knowledge-distillation-works-in","title":"Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation","date":"2025-05-19","arxiv_id":"2505.13111","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-frameworks-unpacking-collaboration","title":"Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems","date":"2025-05-18","arxiv_id":"2505.12467","repositories_listed":0,"syntology":null},{"url":null,"slug":"calm-co-evolution-of-algorithms-and-language","title":"CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design","date":"2025-05-18","arxiv_id":"2505.12285","repositories_listed":0,"syntology":null},{"url":null,"slug":"ds-progen-a-dual-structure-deep-language","title":"DS-ProGen: A Dual-Structure Deep Language Model for Functional Protein Design","date":"2025-05-18","arxiv_id":"2505.12511","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-n-gram-to-attention-how-model","title":"From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modeling","date":"2025-05-18","arxiv_id":"2505.12381","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-based-user-simulation-for-low-knowledge","title":"LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems","date":"2025-05-18","arxiv_id":"2505.13528","repositories_listed":0,"syntology":null},{"url":null,"slug":"mclm-a-function-infused-and-synthesis","title":"mCLM: A Function-Infused and Synthesis-Friendly Modular Chemical Language Model","date":"2025-05-18","arxiv_id":"2505.12565","repositories_listed":0,"syntology":null}],"record_sha256":"676ccea184d19bc36eab4a06de86794b3db48ca50b6cb3e3a1ceb55fc92410a4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}