Xi'an Jiaotong University

Large language models refuse the same harmful request in one language but may comply when it is rephrased in another. Researchers first identified safety-related neurons independently within each language, then took the intersection of the candidate sets from six languages to obtain a cross-lingually shared "safety kernel," and tested its functional role with activation suppression and activation-state transfer. Building on it, SK-Masked LoRA restricts fine-tuning updates to the feed-forward network output dimensions corresponding to the safety kernel, lowering attack success rates across several models and multilingual safety benchmarks, with some effect on languages excluded from kernel discovery.

Large language models refuse the same harmful request in one language but may comply when it is rephrased in another. Researchers first identified safety-related neurons independently within each language, then took the intersection of the candidate sets from six languages to obtain a cross-lingually shared "safety kernel," and tested its functional role with activation suppression and activation-state transfer. Building on it, SK-Masked LoRA restricts fine-tuning updates to the feed-forward network output dimensions corresponding to the safety kernel, lowering attack success rates across several models and multilingual safety benchmarks, with some effect on languages excluded from kernel discovery.

Remote-sensing image fusion and semantic interpretation have usually been optimized separately, so good fusion metrics need not preserve downstream retrieval or detection utility. Lance maps each input to a closed-vocabulary text record of scene, objects and layout, conditions fusion on that language, re-describes the fused image as text, and back-propagates through text consistency and an anti-collapse text–mask contrastive loss with negative queries. Across seven test sets on GF2, QuickBird, WorldView-III and WorldView-II, reduced-scale reference metrics improve by up to 11.7% (median 2.1%) over the strongest learning baseline, and a held-out RemoteCLIP verifier plus a supervised DOTA detector give +6.4 mAP@0.5 over the closest competitor.

Remote-sensing image fusion and semantic interpretation have usually been optimized separately, so good fusion metrics need not preserve downstream retrieval or detection utility. Lance maps each input to a closed-vocabulary text record of scene, objects and layout, conditions fusion on that language, re-describes the fused image as text, and back-propagates through text consistency and an anti-collapse text–mask contrastive loss with negative queries. Across seven test sets on GF2, QuickBird, WorldView-III and WorldView-II, reduced-scale reference metrics improve by up to 11.7% (median 2.1%) over the strongest learning baseline, and a held-out RemoteCLIP verifier plus a supervised DOTA detector give +6.4 mAP@0.5 over the closest competitor.

Large reasoning models often keep deliberating after enough information is available, raising decoding latency and memory cost. LoCo moves the compression decision to individual reasoning states: it finds candidate overthinking states in the model's own traces, freezes that prefix, regenerates shorter continuations whose answers verify as correct, and learns a continue-or-conclude preference with DPO. Across five math benchmarks, completion length drops 41.7%–45.4% while accuracy holds or improves; trained on math only, the same model cuts length by 23.4%–36.3% on three code benchmarks.

Large reasoning models often keep deliberating after enough information is available, raising decoding latency and memory cost. LoCo moves the compression decision to individual reasoning states: it finds candidate overthinking states in the model's own traces, freezes that prefix, regenerates shorter continuations whose answers verify as correct, and learns a continue-or-conclude preference with DPO. Across five math benchmarks, completion length drops 41.7%–45.4% while accuracy holds or improves; trained on math only, the same model cuts length by 23.4%–36.3% on three code benchmarks.

The authors introduce Ego2World, a benchmark that compiles annotated cooking activities into executable planning environments under partial observation, linking source steps and objects to symbolic action rules, persistent world states, and explicit task conditions while maintaining world state and agent belief separately; evaluating six planners on 105 tasks shows accepted operations often leave task goals unmet, and execution traces and condition checks distinguish interrupted runs, partial attainment, and completed execution without goal attainment; in a separate paired Qwen-Plus study, persistent belief improves action validity by 4.15 percentage points and reduces visual-query attempts by 90.27%, with higher token use and no detected completion gain.

The authors introduce Ego2World, a benchmark that compiles annotated cooking activities into executable planning environments under partial observation, linking source steps and objects to symbolic action rules, persistent world states, and explicit task conditions while maintaining world state and agent belief separately; evaluating six planners on 105 tasks shows accepted operations often leave task goals unmet, and execution traces and condition checks distinguish interrupted runs, partial attainment, and completed execution without goal attainment; in a separate paired Qwen-Plus study, persistent belief improves action validity by 4.15 percentage points and reduces visual-query attempts by 90.27%, with higher token use and no detected completion gain.

This work presents a unified theoretical analysis of sparse attention: it proves that the Jensen–Shannon divergence between full and sparse attention is determined solely by the discarded truncation mass with a closed-form expression, uses order statistics under i.i.d. sub-Gaussian attention-score assumptions to show that the high-probability lower bound on truncation mass increases with sequence length, and derives sparsity-tightened generalization bounds via Rademacher complexity and a Xu–Raginsky mutual-information bound with entropy and covering-number analysis, verifying the closed-form divergence and the growth of information loss on GPT-2 (124M) with WikiText-103.

This work presents a unified theoretical analysis of sparse attention: it proves that the Jensen–Shannon divergence between full and sparse attention is determined solely by the discarded truncation mass with a closed-form expression, uses order statistics under i.i.d. sub-Gaussian attention-score assumptions to show that the high-probability lower bound on truncation mass increases with sequence length, and derives sparsity-tightened generalization bounds via Rademacher complexity and a Xu–Raginsky mutual-information bound with entropy and covering-number analysis, verifying the closed-form divergence and the growth of information loss on GPT-2 (124M) with WikiText-103.